BRN Discussion Ongoing

[stockduck]

Just a thought...a little bit offtopic:

I recently went to the hairdresser, as most of us do a few times a year. The former master hairdresser has handed over his business to the younger generation, but still works enthusiastically. Here's the problem, which I believe could lead to a new product with high global sales.

The hands, with their bones, tendons and muscles, are subject to severe wear and tear in the hairdressing trade, which could be reduced by a precise, effective and efficient high-performance exoskeleton. I would suggest that it makes more sense to develop such products equipped with intelligent sensors than robots for domestic use. Mass-produced goods made of injection-moulded plastic parts and weighing very little.

In gardening, electronic shears are used as a substitute for manual labour, but in my opinion, this cannot be transferred to hairdressing.

Perhaps the management knows a customer, who is interested in such a product and sees a future for it. (One battery change per working day, for example).

It is likely that such an exoskeleton could also be extended to other professions.


Translated with DeepL.com (free version)

 

[stockduck]

...only dot joining....

https://www.nordicsemi.com/Nordic-news/2026/03/Nordic-Semiconductor-introduces-precise-adaptive-battery-health-monitoring-for-IoT-devices

New fuel gauge solution delivers State‑of‑Health reporting, adaptive battery modeling, and seamless fleet observability via nRF Cloud powered by Memfault.​

.

https://www.nordicsemi.com/Nordic-news/2026/03/Nordic-Semiconductor-expands-nRF54L-Series-with-entry-level-Bluetooth-LE-SoCs

....
The nRF54LS05A and nRF54LS05B combine a 128 MHz Arm® Cortex® M33 with low-leakage RAM for efficient, responsive processing in compact, ultra-low-power wireless designs.....

 

[Frangipani]

James Shields (our VP of Sales & Business Development) and Ivan Projić (CEO of Neuromorphyx) at the BrainChip booth at embedded world 2026 earlier today:

 

[Frangipani]

As suspected, the recent article that claimed BrainChip “had secured an order from Nex Novus for medical sensing applications” was wrong:

There will be a live demo of the made-in-Croatia Neuromorphyx Vision NeuroNode at the BrainChip booth at Embedded World 2026 in Nürnberg (10—12 March).

“Experience the Vision NeuroNode™ tiny, compact and rugged form in-person! Featuring the AKD1500 neuromorphic co-processor from Brainchip Inc. pushing the boundaries of high-performance, low-latency, Spiking Neural Networks (SNN) for energy efficient edge AI.

POWER & COMPUTE EFFICIENCY < 300 mW while delivering 800 GOPS
ON-CHIP LOCAL MEMORY 1 MB
CLOCK FREQUENCY RANGE 5 – 400 MHz
SILICON PROCESS 22 nm FD-SOI CMOS digital logic
PACKAGE 7×7 mm MFCTFBGA169, 0.5 mm pitch

Find us at:
Hall 5 / Booth 5-213 (10 - 12 March 2026. Nuremberg, Germany)

NeuroNode™​

Deployment time - seconds.
Operational lifetime - years.
Scalability factor - unparalleled.

Rugged build.
Always-on sensing.
Energy-efficient processing.
Battery-powered operation.
Low-latency reactions.

The Vision NeuroNode™ is armed with an FPGA, a neuromorphic AI accelerator and an event-based neuromorphic vision sensor.
Our IP and architecture, allows up to multiple-years* of field operation on a single battery pack integrated in our compact 5x5x5cm IP67 case.
*Depending on scene activity and inference.

We offer solar panels and add-on battery packs as attachments that further prolong the operational life-time and extend capabilities.

• Fast tracking, equivalent to >10.000 FPS
• Extreme lightning conditions >120dB
• Native power efficiency <10mW

Technology developed by Prophesee and Sony.
Skillfully engineered into compact modules by CenturyArks.
We offer a wide range of sensors and lenses to meet our client requirements depending on deployment location, terrain and field conditions.
HD 1280 x 720 Sony IMX636 / IMX646 (via CenturyArks)
VGA 640 x 512 Sony IMX 637 / 647 (via CenturyArks)
320 x 320 ultra low-power GENX320 (via Prophesee)
Explore sensor features in the Sensor options section →”

[…]

NeuroHive™​

Vision, Audio, Radar, IMU are different NeuroNodes™ forming the hive mind network. Distributed intelligence, at the edge.

NeuroHive™ provides your team with the ability to gather mission critical intel from the field, live. Scalable and reliable.

Over-the-air SNN model switching.
Tracking target velocity and direction.
Fleet management.
Orchestrated systems.
External API triggers.
Integration to existing systems and comms.”

Neuromorphyx™ - Edge AI Networks

Networks of neuromorphic edge AI nodes. Distributed by hardware. Unified by software. Sense. Think. Decide. On the edge. NeuroNodes™ managed via NeuroHive™.

neuromorphyx.com

View attachment 95475 View attachment 95476 View attachment 95477 View attachment 95478 View attachment 95479 View attachment 95480 View attachment 95481 View attachment 95483
View attachment 95482

Here is today’s official press release:

https://www.businesswire.com/news/home/20260305665563/en/BrainChip-Announces-Neuromorphyx-as-Strategic-Customer-and-Go-to-Market-Partner-for-AKD1500-Neuromorphic-Processor

Mar 5, 2026 9:00 AM Eastern Standard Time

BrainChip Announces Neuromorphyx as Strategic Customer and Go-to-Market Partner for AKD1500 Neuromorphic Processor​

---

LAGUNA HILLS, Calif.--(BUSINESS WIRE)--BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world leader in ultra-low power, fully digital, event-based neuromorphic AI, today announced that Nex Novus d.o.o., Neuromorphyx™ has selected the Akida™ AKD1500 co-processor for evaluation and integration in its Vision NeuroNode™ edge-AI device.



This strategic engagement and partnership agreement expands BrainChip’s reach into defense, robotics and industrial edge sensing. By integrating the AKD1500 into Neuromorphyx’s rugged, modular architecture, the companies are enabling always-on intelligence where power, bandwidth and connectivity are constrained.

Enabling Scalable, Always-on Edge Intelligence
The AKD1500 will be integrated into Neuromorphyx’s modular NeuroBlocks™ architecture: SensorBlock™ (DVS/EVS), BridgeBlock™ (FPGA), BrainBlock™ (AKD1500) and InterfaceBlock™, forming a key compute element within the Vision NeuroNode™ device and its NeuroHive™ fleet orchestration platform. By leveraging BrainChip’s Akida™ technology, Neuromorphyx is building configurable edge nodes for real-time detection and tracking using event-based vision and other sensors such as audio, radar and IMU:

• Ultra-low power, always-on inference: AKD1500 supports mission-critical detection pipelines within tight power budgets, operating at milliwatt power levels (under 300mW for high-performance tasks), enabling battery deployments matching the core NeuroNode feature of multi-year field operations on a single integrated battery.
• Low-latency sparse processing: Paired with event-based vision sensors, NeuroNode™ can convert event streams into compact spatiotemporal tensors and run them on AKD1500, where Akida’s event-based execution exploits activation sparsity to reduce data movement and accelerate response.
• Configurable deployment at scale: AKD1500’s 1 MB on-chip memory enables NeuroNode™ to run fully self-contained neuromorphic SNN models without external DRAM, reducing power, latency, and attack surface while enabling deterministic real-time response.

The Potential: Networked NeuroNodes at Scale

Neuromorphyx’s approach to in-house manufacturing scalability paired with AKD1500 competitive pricing, allows for compact NeuroNodes to have simple deployments even in tens of thousands of units by forming networks that cover vast areas managed with NeuroHive™: a map-based platform for deploying, monitoring and updating these edge nodes across sites. The platform supports coordinated sensing, target analytics (including velocity and direction), and external API triggers for integration into existing command-and-control or industrial systems, while natively maintaining privacy and keeping processing at the edge.

"Our mission has always been to bring AI to the edge where it is most needed," said Sean Hehir, CEO of BrainChip. "Neuromorphyx is building a compelling, modular platform for deploying always-on intelligence in demanding environments. By combining event-driven sensing with Akida’s ultra-low power neuromorphic processing, we’re helping enable scalable edge AI for defense, industrial monitoring and autonomous systems."

About Neuromorphyx™ and Nex Novus d.o.o.
Neuromorphyx™ is a deep-tech hardware and embedded software company, spun out of Nex Novus d.o.o., focused on high-performance, energy-efficient edge AI for defense, robotics and industrial sensing. Its modular NeuroBlocks™ architecture enables configurable edge AI devices, NeuroNodes™, built around advanced sensors, including event-based vision, audio, radar, IMU and a choice of accelerator technologies. Neuromorphyx’s NeuroHive™ platform provides fleet management, orchestration and secure over-the-air model updates.

About BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY):
BrainChip is the worldwide leader in Edge AI on-chip processing and learning. The company’s first-to-market, fully digital, event-based AI processor, Akida™, uses neuromorphic principles to mimic the human brain, analyzing only essential sensor inputs with unmatched efficiency and energy economy. Explore more at www.brainchip.com.

Contacts​

Media Contact
Madeline Coe
prforbrainchip@bospar.com
224-433-9056

Some more info provided by Neuromorphyx in the above video and below comment about the nature of potential customers they have in mind:

BrainBlock™ in Vision NeuroNode stack | Neuromorphyx

🧠 Big News!⚡Partnership with BrainChip enables our SNNs to detect mission-critical events at a fraction of the cost. AKD1500, the neuromorphic "Brain" of our modular hardware architecture. Financial Times BusinessWire Read about our recent partnership 👉 https://lnkd.in/drMyena9 See it live...

www.linkedin.com

 

[stockduck]

BrainChip Enables the Next Generation of Always-On Wearables with the AkidaTag© Reference Platform

New Platform for wearable AI and industrial uses combines the company’s Akida AKD1500 neuromorphic co-processor silicon with Nordic Semiconductor’s nRF5340...

semiiphub.com

....

Availability:​

The reference platform is licensed to accelerate development for OEMs and system integrators; including hardware schematics, firmware, and a companion mobile application. It will be available for evaluation in May 2026, with volume in Q3 2026.
.....

 

[Frangipani]

Just a thought...a little bit offtopic:

I recently went to the hairdresser, as most of us do a few times a year. The former master hairdresser has handed over his business to the younger generation, but still works enthusiastically. Here's the problem, which I believe could lead to a new product with high global sales.

The hands, with their bones, tendons and muscles, are subject to severe wear and tear in the hairdressing trade, which could be reduced by a precise, effective and efficient high-performance exoskeleton. I would suggest that it makes more sense to develop such products equipped with intelligent sensors than robots for domestic use. Mass-produced goods made of injection-moulded plastic parts and weighing very little.

In gardening, electronic shears are used as a substitute for manual labour, but in my opinion, this cannot be transferred to hairdressing.

Perhaps the management knows a customer, who is interested in such a product and sees a future for it. (One battery change per working day, for example).

It is likely that such an exoskeleton could also be extended to other professions.


Translated with DeepL.com (free version)

You will find that there are already exoskeletons available adapted to the needs of hairdressers (and many other professions), although they don’t support their hands as such (which I assume would be difficult, as the job requires nimble fingers), but help to reduce fatigue and relieve pain, typically in the arms, shoulders, neck, and upper back. This in turn of course benefits the hands as well.

Exoskeletons for hairdressers

Hapo exoskeletons are an innovative and effective solution to improve the daily lives of hairdressers and limit their pain related to musculoskeletal disorders.

www.hapo.eu

Also check out SuitX by Ottobock for exoskeletons in general - some motorised, others not:

https://www.suitx.com/de/startseite

https://www.suitx.com/en/about-suitx

One of their use cases: IKEA

https://www.suitx.com/de/logistik/IKEA

IKEA boosts workplace health with 400+ exoskeletons deployed across 14 countries | Ingka Group

In a significant step towards improving workplace ergonomics, IKEA has deployed 400+ exoskeletons across 14 countries, marking a major milestone in its commitment to creating a better everyday life - not only for customers, but for its co-workers too.

www.ingka.com

IMO definitely a future market for neuromorphic technology.

 

[Frangipani]

#embeddedworld2026 #neuromorphicai #edgeai #akida #brainchip | BrainChip

The doors are open. 👋 Embedded World 2026 has officially kicked off in Nuremberg and we're ready. Come find us at Hall 5, Stand 5-213 to see how neuromorphic AI is redefining what's possible at the edge. Whether you're exploring smarter sensing, ultra-low power inference, or the future of...

www.linkedin.com

 

[Pom down under]

What the actual FK is going on here.
Now we're relying for some random IBM guy making music for our revenue? FFS
Can we just vote these clowns out for not meeting they performance targets!!

Wish we could just vote a few clowns out from here, mention no names

 

[Frangipani]

Linas BeliūnasLinas Beliūnas • 3rd+Premium • 3rd+Building a Safer Internet with AI | Scouting for top startups to invest in | The only newsletter you need for Finance & Tech at linas.substack.com | Financial Technology | FinTech | Artificial Intelligence | VCBuilding a Safer Internet with AI | Scouting for top startups to invest in | The only newsletter you need for Finance & Tech at linas.substack.com | Financial Technology | FinTech | Artificial Intelligence | VC
Visit my website
1d • Edited • 1 day ago • Edited • Visible to anyone on or off LinkedIn
Follow

Wild: Scientists just built a biological computer that runs DOOM using living neurons. No AI model was involved, and the entire system fits in a shoebox

Australian startup Cortical Labs just showed a system where ~200,000 lab-grown human neurons control the classic shooter Doom.

No code runs inside the cells.
No gradient descent.
No training dataset.

Just biology learning

The setup is almost surreal:

→ A shoebox-sized biological computer called CL1 keeps neurons alive with nutrients, temperature control, and waste removal.
→ Game information is sent as electrical signals directly to the cells.
→ The neurons’ spikes are decoded into game actions: move, turn, shoot.
→ The culture learns during the session, adapting to threats and navigation.

This builds on their earlier DishBrain experiment that learned to play Pong.

But Doom is different.

Now you need 3D movement, aiming, and threat detection - all handled by a tiny living network.

And the energy numbers are wild:

↳ A rack of ~30 CL1 units runs on under 1 kW
↳ That’s orders of magnitude less power than comparable silicon AI workloads

Which means that ontelligence may not require massive GPU clusters.

It might emerge from physics + feedback.

Silicon gives us speed.
Biology gives us efficiency and plasticity.

The interesting future might be hybrid systems - chips doing math, neurons doing adaptation.

And if we can grow intelligence, we may soon need to rethink what actually counts as a computer…

P.S. also check out how to Turn Claude Cowork Into Your Personal COO that does the work while you sleep : https://lnkd.in/eS6JCk2G


Play
Loaded: 100.00%



Remaining time 0:01
1x
Playback speed
Unmute

Turn fullscreen on

• 
  
  
  1,093
• • 263 comments
  • 184 reposts

Reactions​

• 
  
• 
  
• 
  
• 
  
• 
  
• 
  
• 
  
• 
  
• …

Like
Comment

Repost



Send




Add a comment…
Open Emoji Keyboard



Current selected sort order is Most relevantMost relevant

Peter Van Der Made • Following​

Founder and Director at BrainChip Holdings Limited
1h


I think the same could be true for the Akida 1500 neuromorphic network. In its native mode it learns from spiking input and it has more neurons.


Like

9

Reply2 replies2 Replies on Peter Van Der Made’s comment

See previous replies

Kevin D. Johnson • Following​

Field CTO – HPC, AI, LLM & Quantum Computing | Principal HPC Cloud Technical Specialist at IBM | Symphony • GPFS • LSF
1h


Peter Van Der Made Now that would make for a cool demo!


Like

1

Reply

Interesting comment by Peter van der Made on this article:
https://www.linkedin.com/posts/lina...p&rcm=ACoAADiF7m8BeC0VWjTq7u7m7GZMljs7rpBFkJw
View attachment 95912
View attachment 95913
Greetings from Germany!

Sign Up | LinkedIn

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

www.linkedin.com

 

[Boab]

Sign Up | LinkedIn

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

www.linkedin.com

View attachment 95920

Kevin, you are an absolute Jet.

 

[Frangipani]

Today’s post by femtoAI (formerly known as Femtosense) is a reminder that
1. AFRL is engaged with several neuromorphic players…
2. our customers - Neuromorphyx in this particular case - are also keenly watching what our competitors in the edge space are doing…

#eventbasedsensing #computervision #edgeai #aihardware #neuromorphic #defensetech #robotics #xr | femtoAI

Event-based sensors (EBS), such as those developed by PROPHESEE, have enormous untapped potential. By outputting only pixel-level changes asynchronously rather than full image frames, these sensors achieve microsecond-scale temporal resolution, over 120 dB of dynamic range, and milliwatt-level...

www.linkedin.com

TRL = Technology Readiness Level
CRL = Commercial Readiness Level

---

LinkedIn Login, Sign in | LinkedIn

Login to LinkedIn to keep in touch with people you know, share ideas, and build your career.

www.linkedin.com

---

femtoAI - Empowering Intelligence in Everyday Devices

Embedded AI platform built upon a unique AI accelerator capable of delivering higher performance at lower latency, using less energy in smaller silicon.

femto.ai

 

[buena suerte :-)]

Snap haha

BrainChip Enables the Next Generation of Always-On Wearables With the AkidaTag© Reference Platform

None

lasvegassun.com

BrainChip Enables the Next Generation of Always-On Wearables With the AkidaTag© Reference Platform​

Published Tuesday, March 10, 2026 | 6 a.m.

Updated 48 minutes ago

LAGUNA HILLS, Calif.--(BUSINESS WIRE)--Mar 10, 2026--
BrainChip Holdings Ltd. (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low-power, fully digital, event-based neuromorphic AI, today announced at Embedded World in Nuremberg, Germany the launch of AkidaTag ©, a reference platform for smart sensing in a battery-powered tag powered by Nordic Semiconductor.
Intelligent wearable and remote industrial sensors can deliver always-on sensing on a battery without relying on a connection to a mobile device, PC or the cloud. Offering on-device adaptive learning allows personalization of the model while in use on-device, addressing the challenge of “one-size-fits-all” trained models and reducing the need to transmit data off the device for retraining on a GPU. OEMs can rapidly develop products based on the AkidaTag reference design using design partners.
BrainChip AKD1500 operates as a dedicated neuromorphic AI co-processor, delivering optimal energy efficiency while the Nordic nRF5340 wireless SoC handles connectivity, sensor management, and application logic. This provides a foundation for wearables and remote sensing device manufacturers to build devices that can interpret and communicate information effectively. AkidaTag features connectivity through Nordic Semiconductor’s nRF5340 Bluetooth ® Low Energy (LE) SoC on-device wireless communications. A BrainChip-developed mobile application utilizes this connection to set up configuration, load, and update models and firmware as well as receive diagnostics, logging, and alerts to the mobile device.
AkidaTag offers a blueprint and development kit with full design, hardware, firmware, and mechanicals that enable wearables makers and other manufacturers to build devices that can:

• Monitor biological signals for health and wellness applications while preserving privacy through fully on-device processing. Low power usage allows for days of monitoring vital health signals.
• Detect anomalies in vibration and motion for classification in industrial equipment, enabling predictive maintenance.
• Voice wake-up commands for intelligent interfaces.
• Acoustic ambient environment detection and classification.
• Personalization of the device AI model using on-device edge learning and self-learning through neuromorphic principles.

“At BrainChip, we are committed to pushing the boundaries of what is possible at the edge,” said Sean Hehir, CEO of BrainChip. “By leveraging the robust ecosystem of Nordic Semiconductor, we are providing product designers with a blueprint for the future of wearables that’s always-on, privacy-first, and self-learning. This platform proves that high-performance AI and long battery life are no longer mutually exclusive.”
“Seeing BrainChip use our technology to enable always-on neuromorphic AI demonstrates the potential of our wireless SoCs to drive the next wave of innovation in wearable and connected health markets,” said Petter Myhre, Product Marketing Director at Nordic Semiconductor. “The nRF5340 is the world’s first wireless SoC with two Arm® Cortex®-M33 processors, making it the perfect choice for complex IoT applications that require both high performance and extreme energy efficiency.”
BrainChip will highlight the AkidaTag’s capabilities at Embedded World (Hall 5, booth 5-213) through a self-contained battery-powered “puck.” This will feature an integrated accelerometer for motion detection and a microphone for voice and vibration recognition. It can perform various functions, including keyword spotting, anomaly detection, and voice-activated wake-up. Control is through a mobile app that dynamically displays results and enables users to download activities for analysis.
Availability: The reference platform is licensed to accelerate development for OEMs and system integrators; including hardware schematics, firmware, and a companion mobile application. It will be available for evaluation in May 2026, with volume in Q3 2026.

BrainChip Enables the Next Generation of Always-On Wearables With the AkidaTag© Reference Platform​

BrainChip's new tag keeps health and industrial sensors always on

On-device learning and Nordic wireless tech power BrainChip's AkidaTag for always-on wearables and industrial sensors, with OEM kits arriving May–Q3 2026.

www.stocktitan.net

Thanks guys Exciting news

BrainChip Enables the Next Generation of Always-On Wearables With the AkidaTag© Reference Platform​

Just seeing this makes me feel 'Warm and fuzzy'

..........AkidaTag©...........​

Bring it home BRN

Good Luck all

 

[Boab]

Sign Up | LinkedIn

500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

www.linkedin.com

View attachment 95920

Does this mean that Kevin is going to look at AKIDA 1500 as per PVDM's comment?

"I think the same could be true for the Akida 1500 neuromorphic network. In its native mode it learns from spiking input and it has more neurons."

 

[Frangipani]

Guten Tag, AkidaTag!

Akida TAG LP

Why AkidaTag Changes Edge AI Always-On Continuous AI inference with ultra-low power consumption. Enable keyword spotting, gesture recognition, and anomaly detection while maintaining multi-day battery life. Privacy-First All data is processed locally on the

brainchip.com

 

[keyeat]

James Shields (our VP of Sales & Business Development) and Ivan Projić (CEO of Neuromorphyx) at the BrainChip booth at embedded world 2026 earlier today:






View attachment 95917


View attachment 95916

Wow what a performance from James Shields ! Comparing this with Ivan Projić ......

 

[buena suerte :-)]

Getting a heap of exposure

 

[Jacob Kiraz]

Getting a heap of exposure



View attachment 95933
View attachment 95934


View attachment 95935


View attachment 95938


View attachment 95942

My Question is why isnt the company relaying the news with shareholders

 

[Terroni2105]

Maybe we have been playing with Nordic since 2024 as I posted the below back in Dec 24 regarding something I picked up on GitHub with BRN India and Nordic NRF5 series SOCs.

The news just released involves a NRF5 series (340)

BRN Discussion Ongoing

quantum brilliance is developing a diamond-based room-temperature quantum processor: https://quantumbrilliance.com/press-release/quantum-brilliance-announces-first-purchase-of-a-room-temperature-quantum-accelerator-in-europe-powered-by-nvidia-cuda-q They place nitrogen (N) atoms in the...

thestockexchange.com.au

I did a search on a keyword and found @Sirod69 had been looking at it some time ago (though she sadly hasn't been seen for a few months?) as this evening I found what I thought could be an interesting entry on Github regarding the open source Zephyr RTOS.

Brainchip-India lodged a Documentation Issue a couple of days ago.

Now, is Brainchip-India "our" Indian team?.....can't think of any other Brainchip in India that might be playing with RTOS (Real Time Operating Systems) for SOCs.

Anyway, what caught my eye was the issue being related to the below and in particular "Nordic" SOCs.

Is it conceivable that our team are either playing with the Nordic NRF5 series of SOCs of their own accord or potentially (& preferably) at the request of a client using one of the NRF5 series SOCs?

Or is it a non (SNN) event...pun intended.

doc: Documentation issue in 'develop/flash_debug/nordic_segger' · Issue #83191 · zephyrproject-rtos/zephyr​

Describe the bug << Please describe the issue here >> << Looks like the tool mentioned "nrfjprog" to flash elf onto nRF board is no longer available and the official nRF came-up with a common "nrfu...
github.com

Some background on Zephyr

Zephyr Project​

The Zephyr Project is a Linux Foundation hosted Collaboration Project.

zephyrproject.org

Hi FMF

not sure if related.

they are hiring a new job in India, Senior Machine Learning Engineer.
it is on LinkedIn, Posted about 11 hr ago but I can’t link it to here.

About the job​

At Brainchip’s India Design Center (Hyderabad), we’re actively looking for senior AI/ML engineers to build software in embedded environments built around Brainchip SoCs/IP’s, to perform advanced AI tasks in various domains.


Requirements:

• BTech/MS/MTech in Electronics/Electrical/Computer/Software Engineering
• 8-15 years of proven experience in software development, with at least 4 years in building AI/ML Software (building/training Models, Inference, performance metrics etc.) in any AI/ML environment (Keras/TensorFlow/TF-Lite/PyTorch etc.)
• Working experience in Python, C++; OOAD skills are a plus
• Programming experience in embedded environments & event-driven programming a plus
• Experience in working as part of Agile/SCRUM Teams
• Ability to build code that works in resource-constrained environments
• Strong interpersonal skills and ability to work with remote Teams with diverse backgrounds
• Decent communication skills (verbal, written and documentation)
• Good knowledge of software development life cycle, especially in AI domain

Some background on the Nordic nRF5 series of SOCs of which a lot end uses appear in our wheelhouse.

Search​

Nordic Semiconductor
www.nordicsemi.com

​

 

[Bravo]

Maybe we have been playing with Nordic since 2024 as I posted the below back in Dec 24 regarding something I picked up on GitHub with BRN India and Nordic NRF5 series SOCs.

The news just released involves a NRF5 series (340)

BRN Discussion Ongoing

quantum brilliance is developing a diamond-based room-temperature quantum processor: https://quantumbrilliance.com/press-release/quantum-brilliance-announces-first-purchase-of-a-room-temperature-quantum-accelerator-in-europe-powered-by-nvidia-cuda-q They place nitrogen (N) atoms in the...

thestockexchange.com.au

I did a search on a keyword and found @Sirod69 had been looking at it some time ago (though she sadly hasn't been seen for a few months?) as this evening I found what I thought could be an interesting entry on Github regarding the open source Zephyr RTOS.

Brainchip-India lodged a Documentation Issue a couple of days ago.

Now, is Brainchip-India "our" Indian team?.....can't think of any other Brainchip in India that might be playing with RTOS (Real Time Operating Systems) for SOCs.

Anyway, what caught my eye was the issue being related to the below and in particular "Nordic" SOCs.

Is it conceivable that our team are either playing with the Nordic NRF5 series of SOCs of their own accord or potentially (& preferably) at the request of a client using one of the NRF5 series SOCs?

Or is it a non (SNN) event...pun intended.

doc: Documentation issue in 'develop/flash_debug/nordic_segger' · Issue #83191 · zephyrproject-rtos/zephyr​

Describe the bug << Please describe the issue here >> << Looks like the tool mentioned "nrfjprog" to flash elf onto nRF board is no longer available and the official nRF came-up with a common "nrfu...
github.com

Some background on Zephyr

Zephyr Project​

The Zephyr Project is a Linux Foundation hosted Collaboration Project.

zephyrproject.org

Some background on the Nordic nRF5 series of SOCs of which a lot end uses appear in our wheelhouse.

Search​

Nordic Semiconductor
www.nordicsemi.com

​

Hi FMF,

The Nordic partnership in the AkidaTag announcement certainly is an interesting development.

Nordic Semiconductor is a pretty serious player; one of the dominant chip suppliers for low-power wireless devices.Their chips are used in wearables, medical devices, asset tracking tags, smart home sensors, industrial IoT nodes.

Some of the companies using Nordic chips include:

• Fitbit / Google wearables
• Garmin devices
• medical monitoring devices
• industrial sensor platforms

Nordic als has a huge developer community. By providing a reference design, BrainChip allows those developers to test Akida without designing hardware from scratch, which is obviously a plus.

I asked ChatGPT about the choice of the Nordic nRF5340 as a co-processor and what devices it's commonly used in and here's what it had to say.





ChatGPT's Response

The nRF5340 from Nordic Semiconductor is a dual-core Bluetooth Low Energy (BLE) system-on-chip widely used in battery-powered IoT and wearable devices that need strong connectivity, security, and low power consumption.
Rather than appearing in one famous consumer product, it’s commonly used by OEMs as the core chip inside many different devices. Here are the main device categories where it is deployed.

---

1. Wearables and Health Devices​

The nRF5340 is popular in health and fitness wearables because it can run sensors continuously while maintaining long battery life.
Typical devices include:

• Fitness trackers
• Smart rings
• Heart-rate monitors
• Sleep monitoring devices
• Continuous health monitoring wearables
• Rehabilitation and physiotherapy wearables

These devices often monitor signals like:

• motion (accelerometers)
• heart rate
• respiration
• temperature.

---

2. Wireless Audio Devices​

Nordic designed the nRF5340 specifically with Bluetooth LE Audio support, so it is widely used in:

• True wireless earbuds
• Hearing aids
• Wireless microphones
• Audio streaming accessories

Many next-generation Auracast / LE Audio earbuds use this chip family.

---

3. Asset Tracking and Smart Tags​

A very common application is industrial or logistics tracking tags, which is why BrainChip’s platform is called AkidaTag.
Examples include:

• Asset tracking tags for warehouses
• Equipment monitoring tags
• Livestock tracking devices
• Smart shipping labels
• Smart luggage tags

These devices typically transmit small packets of sensor data over BLE.

---

4. Industrial IoT Sensors​

Industrial companies use the nRF5340 for predictive maintenance sensors.
Typical devices:

• vibration monitoring sensors
• temperature monitoring nodes
• environmental sensors
• machine health monitoring devices

Factories attach these sensors to equipment so they can detect:

• abnormal vibration
• overheating
• mechanical wear.

---

5. Smart Home Devices​

The chip is also used in many smart home products, including:

• smart locks
• motion detectors
• smart lighting controllers
• occupancy sensors
• environmental monitors.

These devices require secure wireless connectivity with long battery life.

---

6. Medical and Clinical Devices​

Because Nordic chips support strong security and low power, they are also used in medical devices, such as:

• portable patient monitoring systems
• wearable ECG monitors
• glucose monitoring accessories
• remote patient telemetry devices.

These products often send data to mobile apps via Bluetooth.

---

7. Human Interface Devices​

The nRF5340 also appears in advanced Bluetooth peripherals like:

• gaming controllers
• keyboards
• wireless mice
• stylus devices.

Its dual-core architecture helps manage input latency and wireless connectivity.

---

Why this chip is popular​

The nRF5340 is widely used because it combines several features that IoT devices need:

• very low power consumption
• Bluetooth Low Energy connectivity
• dual processors for application and networking
• strong security features
• good developer ecosystem

This makes it ideal for devices that must run continuously on small batteries.

---

In the context of BrainChip’s AkidaTag
The architecture looks like this:

Sensors
↓
Akida neuromorphic processor → AI inference
↓
nRF5340 → connectivity + device control + Bluetooth
↓
mobile app or network

So the nRF5340 acts as the communications and system controller, while Akida performs the AI sensing.

---

If you'd like, I can also show you why Nordic chips like the nRF5340 are used in more than 70% of the world's Bluetooth wearables, which explains why BrainChip partnering with that ecosystem could be strategically important.

 

[buena suerte :-)]

My Question is why isnt the company relaying the news with shareholders

I do agree! Just an non price announcement on the ASX would suffice!

But encouraging news moving forwards!