Senior Quantization Engineer - Edge AI

Responsibilities

• Research the latest advancements in model optimization and compression, specifically focusing on neural network quantization, speculative decoding, and pruning.
• Develop and adapt state-of-the-art methods to NXP hardware constraints by building proof-of-concept prototypes.
• Translate research prototypes into robust, optimized production code using C++ and Python.
• Document algorithmic tradeoffs and derive deployment recipes for efficient on-device intelligence.
• Act as a technical bridge between AI Research and Hardware Engineering teams to guide model accuracy and performance decisions.
• Contribute to NXP’s intellectual property portfolio through patents and technical publications.

Requirements

• MSc or Ph.D. in Computer Science, Electrical Engineering, or Mathematics with a focus on Machine Learning or Deep Learning.
• Proven practical experience with CNN architectures and Generative AI (Transformers, LLMs, VLMs).
• Hands-on experience with PyTorch, ONNX, and model conversion/optimization pipelines.
• Proficiency in Python and C++ following best development practices.
• Familiarity with embedded system constraints such as latency, power, and memory bandwidth.

Preferred Qualifications

• Experience with state-of-the-art quantization techniques for discriminative and generative AI (e.g., GPTQ, SpinQuant).
• Experience with NPUs, device-level profiling, and diagnosing memory bottlenecks.
• Experience with custom kernel development.
• Knowledge of MLIR or TVM compilers.

About the Company

NXP is a global leader in secure connectivity solutions for embedded applications, pushing boundaries in the automotive, industrial & IoT, mobile, and communication infrastructure markets to enable a smarter, safer, and more sustainable world.