Senior AI Engineer - Embedded Systems
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Tech stack
+6 more
Job description
Razerβs innovation team in Lille builds prototypes of new technology for Razer hardware and software. We are starting a new area: neural models that run directly on the microcontrollers inside our peripherals (mice, keyboards, headsets, controllers, webcams and new devices).
As Senior AI Engineer - Embedded Systems, you will prototype a wide range of embedded AI applications, from audio and voice to camera vision and sensor data. You will take an idea, choose the model and the silicon, make it run on the target, measure it, and show whether it is worth building. Once a prototype is proven, you hand it over to Razerβs firmware teams, who take it to production.
This is a hands-on role in a small team. You will help set the tools, methods and hardware choices for this area at Razer.
What you will do
- Prototype embedded AI applications for audio (wake word, voice commands, voice activity detection, noise suppression, sound events), vision (presence, face, hand and body detection and landmarks) and other sensor data.
- Select, train or fine-tune, quantise (int8 and below) and optimise models for microcontrollers with and without an NPU (Cortex-M4/M7/M33/M55, Ethos-U, ST Neural-ART and similar).
- Build and maintain the deployment toolchain: TFLite Micro / LiteRT, ExecuTorch, CMSIS-NN, CMSIS-DSP, Vela and vendor compilers.
- Benchmark latency, memory, power and accuracy on real target silicon and development kits, and compare chips for a given use case.
- Write the embedded C/C++ that runs a model end to end: sensor capture, pre-processing (e.g. MFCC, image resize), inference and post-processing.
- Set up camera and microphone data capture on prototypes to build datasets, working with Legal on what data can be collected.
- Check model and dataset licences before a model goes into a prototype.
- Document each prototype (results, limits, what it needs for production) and hand it over to the firmware teams with working code and test data.
- Track new models, silicon and runtimes, and propose which ones are worth testing.
Requirements
- 5+ years of embedded software development in C/C++ on microcontrollers, with at least 2 years deploying ML models on embedded or edge devices. [Years to confirm]
- Hands-on work with Arm Cortex-M and real-time constraints (memory budgets, DMA, interrupts, RTOS or bare metal).
- Experience with model quantisation and at least one MCU inference runtime (TFLite Micro / LiteRT or ExecuTorch).
- Model training and fine-tuning in Python with PyTorch or TensorFlow.
- Basics of audio signal processing (filtering, FFT, MFCC) and/or image processing.
- Comfortable with lab tools: development kits, debuggers, logic analysers, power measurement.
- Able to work alone on open problems, decide fast, and report results plainly.
- Fluent English. French is a plus.
Benefits & conditions
- Ethos-U (Vela), ST Neural-ART / ST Edge AI, NXP eIQ Neutron or another vendor NPU toolchain.
- CMSIS-NN / CMSIS-DSP optimisation, Helium (MVE) or other SIMD.
- Small vision models (detection, landmarks, segmentation) or speech enhancement on constrained devices.
- Zephyr RTOS.
- Experience with audio front ends for headsets or microphones (AEC, beamforming, VAD).
- Published work, open-source contributions or demos in TinyML.
What We Offer
- Work on prototypes that can reach millions of Razer devices.
- A small team with direct access to hardware, firmware and software teams across Razer.
Salary Ranges: β¬55,000.00 - β¬95,000.00 (per annum)
Disclaimer: Exact compensation may vary based on skills, experience, and location.
Razer is proud to be an Equal Opportunity Employer. We believe that diverse teams drive better ideas, better products, and a stronger culture. We are committed to providing an inclusive, respectful, and fair workplace for every employee across all the countries we operate in. We do not discriminate on the basis of race, ethnicity, colour, nationality, ancestry, religion, age, sex, sexual orientation, gender identity or expression, disability, marital status, or any other characteristic protected under local laws. Where needed, we provide reasonable accommodations - including for disability or religious practices - to ensure every team member can perform and contribute at their best.
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Good distractions
Loading talks and stories from around this roleβ¦