Senior Quantization Engineer - Edge AI

Job Title

Senior Quantization Engineer - Edge AI

Role Summary

Senior engineer responsible for research and engineering to optimize neural networks for on-device deployment on NXP Ara2 NPUs. Primary focus is model quantization, with work also covering speculative decoding, pruning and other efficiency techniques for CNNs, LLMs and VLMs.

The role spans prototype research, hardware-aware adaptation, and production implementation, working across AI research, hardware engineering and software teams.

Experience Level

Senior-level. Specific years of experience not stated.

Responsibilities

Key responsibilities center on translating state-of-the-art model optimization research into efficient production implementations and deployment recipes for embedded NPUs.

• Survey and evaluate recent research in model compression and quantization (NeurIPS, ICLR, CVPR and similar venues).
• Prototype and adapt quantization and other optimization methods to NXP hardware constraints; build proofs-of-concept on device.
• Implement robust, optimized production code in C++ and Python, meeting strict memory and compute budgets.
• Document algorithmic trade-offs and produce deployment recipes; mentor engineers on numerical methods and optimization.
• Act as technical liaison between AI research and hardware teams, providing quantitative guidance on accuracy vs. performance trade-offs.
• Contribute to intellectual property through patents and technical publications.

Requirements

Must-have technical skills and practical experience for successful performance in the role.

• Must-have: Practical AI/ML experience with deep understanding of CNNs and generative models (Transformers, LLMs, VLMs).
• Must-have: Hands-on experience with PyTorch, ONNX and model conversion/optimization pipelines.
• Must-have: Proficient software engineering skills in Python and C++ and familiarity with best development practices.
• Must-have: Experience with embedded-system constraints (latency, power, memory bandwidth) and hardware-aware optimization.
• Nice-to-have: Experience with advanced quantization methods (e.g., GPTQ, SpinQuant) and with NPUs or device-level profiling.
• Nice-to-have: Kernel development experience and knowledge of compiler frameworks such as MLIR or TVM.

Education Requirements

Listing cites an MSc or Ph.D. (listed as a plus) in Computer Science, Electrical Engineering, or Mathematics with a focus on Machine Learning or Deep Learning. No other degrees, certifications, or explicit "equivalent experience" language were provided.

About the Company

Company: NXP Semiconductors

Headquarters: Nijmegen, Netherlands

NXP Semiconductors N.V. is a global semiconductor company that provides High Performance Mixed Signal and Standard Product solutions. With over 45,000 employees and operations in more than 35 countries, NXP is a leader in secure connectivity solutions for embedded applications, catering to automotive, industrial IoT, mobile, and communication infrastructure markets. The company is committed to innovation and sustainability, advancing a smarter, safer, and more sustainable world through technology.