GrAI Matter Labs (www.graimatterlabs.ai), a fabless semiconductor company specialized in brain-inspired technology, designs and develops fully programmable ultra-low power neuromorphic HW for sensor analytics and machine learning. The company has offices in Eindhoven (NL), Paris (FR) and San Jose (USA) and has strong relations with top-ranking research groups on neuroscience, human vision and natural computation.
We are looking for R&D Engineer - Machine Learning to join our Architecture team based in Eindhoven. In this role you will develop the Algorithms and Machine Learning solutions that will drive and exercise the revolutionary AI engines embedded in our product Systems on Chip (SoC).
In collaboration with Marketing and Applications teams, you will be responsible for designing, implementing and optimizing domain-specific ML models adapted to the neuromorphic compute architectures.
You will be working on exciting and emerging topics, such as neuromorphic model design, compression, quantization, sparse activation, and efficient hardware implementations. You will be pioneering the development and implementation of neuromorphic computational models and algorithms based on the state-of-the-art machine learning understanding.
Furthermore, you are expected to play a key role in innovation, working with partners on benchmarking and optimizing their applications by efficiently mapping and prototyping them on the company’s architecture, as well as taking such concepts into production-grade systems.
You will be part of a highly diverse international team of skilled engineers and scientists, and you are expected to be a key driver of the team’s further growth.
- Design, implement and optimize domain-specific ML algorithms;
- Define and develop real world applications in selected business verticals in collaboration with our customers and partners;
- Support our ecosystem with sample algorithms and libraries;
- Contribute to the requirement definition of the SW development tools and frameworks for our processor;
- Contribute to the validation of our Neuromorphic processor architectures;
- PhD degree or MSc with 6+ years of experience in Computer Science, Computational Neuroscience, Physics, Mathematics, Electrical/Computer Engineering, or a related field with a focus on machine learning or neuro-inspired computational algorithms and applications;
- Deep knowledge and proven practical experience in a relevant field of research, such as machine learning, computer vision, speech processing, natural language processing, and reinforcement learning;
- Strong understanding of machine learning algorithms and deep networks (CNN, DBN, RNN, LSTM, DCN);
- Experience implementing DL algorithms in high-level languages (e.g. C++, MATLAB, or Python);
- Experience using machine learning toolboxes and libraries (e.g. Caffe, TensorFlow, or PyTorch);
- Experience in developing machine learning solutions for real time, memory constrained systems;
- Ability to write clean, elegant and maintainable production-level code;
- Curious, enthusiastic, fast learner and able to quickly pickup new areas;
- Excellent communication skills in English (both speaking and writing);
Nice to have
- A strong publication record with the top-tier computer vision and machine learning conferences & journals;
- Experience designing, training, and executing spiking neural networks;
- Experience with neuromorphic compute architectures;
- Experience implementing machine learning algorithms on embedded platforms.