Edge AI Model Optimization Research Engineer

What You'll Do

• in everything we do, where every point of view is valued.
• Join us! Job Summary We are searching for a highly skilled AI Research Engineer/Scientist with a deep theoretical background and strong systems engineering skills to contribute to our Edge AI Optimization program, NXP’s initiative towards enabling highly efficient Generative and Agentic AI systems on resource-constrained edge devices.
• You will work at the forefront of innovation, bridging the gap between research and practice, focusing on CNNs, Large Language Model (LLM) and Vision Language Model (VLM) quantization, bringing advanced GenAI and agentic capabilities to NXP NPUs such as Ara-2, directly supporting the future of on-device multimodal intelligence.
• If you want to shape the future of efficient on-device GenAI and Agentic AI, this is the place to be. --- Job Responsibilities 1.
• Research: Actively survey the latest research (NeurIPS, ICLR, CVPR) on neural network quantization.
• Also complementing this with other compression techniques. 2.
• Prototyping: Develop novel ideas and adapt state-of-the-art methods to meet NXP’s specific hardware constraints and performance targets. 3.
• Production Implementation: Translate research prototypes into robust, optimized production code (C++/Python), ensuring strict memory and compute efficiency standards. 4.
• Systems Integration: Document algorithmic tradeoffs, derive deployment recipes, and mentor the engineering team on numerical methods and optimization. 5.
• IP Generation: Contribute to NXP’s intellectual property portfolio through patents and technical publications. --- Job Qualifications Required Background · Education: MSc or Ph.D. in Computer Science, Electrical Engineering, or Mathematics with a specialization in Machine Learning or Deep Learning. · AI Expertise: Proven experience in AI/ML with a deep understanding of CNN architectures and Generative AI (Transformers). · Technical Stack: Strong hands-on experience with PyTorch, TensorFlow, ONNX, and model conversion/optimization pipelines. · Systems Coding: Proficient in Python and C/C++ with an understanding of how code interacts with underlying hardware. · Embedded Mindset: Familiarity with the constraints of embedded systems (latency, power, memory bandwidth).
• Preferred · Hardware Acceleration: Experience with NPUs, device-level profiling, and diagnosing memory bottlenecks. · Tooling: Familiarity with MLOps (MLFlow, ClearML) and Yocto Project. · Advanced AI: Experience with custom kernel development is a plus. · Compilers: Knowledge of MLIR or TVM is a significant plus. #LI-FCC3 More information about NXP in Mexico... #LI-fcc3