Job Title: Quantizer, Research Engineer

Company: NXP Semiconductors México, S. de R.L. de C.V.

We at NXP have an environment that fosters innovation. Our team has technology experts who understand the big picture and mentors who coach passionate professionals to work on the most exciting challenges. We share responsibilities in everything we do, where every point of view is valued. Join us!

Job Summary

Our game-changing AI solutions revolutionize what people and businesses can achieve. NXP inference processors combined with our SDK deliver unrivalled deep learning performance at the edge to accelerate and optimize real-time decision making where every millisecond is critical, and power efficiency is a must. NXP solutions embed high-performance AI into edge devices to create a smarter, safer, and more enjoyable world. Edge AI is on the brink of a boom, and NXP is looking forward to playing a significant role in it.

We are looking for a Research Engineer or Scientist with a deep theoretical background and strong systems engineering skills to lead the evolution of our quantization technology.

This role is ideal for a researcher-practitioner—someone who has tackled open problems in their domain during their PhD and is eager to apply that rigor to production silicon. You will bridge the gap between academic literature and industrial reality, designing novel PTQ/QAT algorithms and implementing them in a high-performance C++ production environment. You will not just implement existing methods; you will invent new ones to ensure customer models run efficiently and reliably on our hardware.

Now tell us your story. We are looking forward to reviewing your application.

Make your mark!

Job Responsibilities

• Research & Innovation: Actively survey the latest research (NeurIPS, ICLR, CVPR) on quantization, compression, and numerical precision. Prototype novel ideas and adapt state-of-the-art methods for NXP’s specific hardware constraints.
• Algorithm Design: Develop mathematically rigorous approximation algorithms (range estimation, bias correction, sophisticated calibration) and mixed-precision strategies with a focus on maximizing accuracy/performance tradeoffs.
• Production Implementation: Translate research prototypes into robust, optimized C++ production code. Own the architecture of the quantization pass, ensuring it meets strict memory and compute constraints.
• Systems Integration: Work at the intersection of theory and practice. Integrate quantization metadata with compilers, runtimes, and kernels, providing quantified guidance on ISA/ABI and micro-architectural impacts to HW architects.
• Rigorous Validation: Design deterministic calibration strategies and representative-dataset samplers. Implement statistical analysis tools to measure and troubleshoot accuracy regressions on complex models (Transformers, CNNs).
• Thought Leadership: Document algorithmic tradeoffs and recipes. Mentor the engineering team on numerical methods and contribute to the company’s intellectual property portfolio.

Job Qualifications

• Ph.D. in Computer Science, Electrical Engineering, or Mathematics with a focus on Machine Learning, Deep Learning, or Numerical Analysis.
• Strong CS Fundamentals & Coding: Unlike typical research roles, this position requires production-grade software engineering skills. You must be proficient in modern C++ (STL, memory management) and Python.
• Mathematical Depth: Deep understanding of linear algebra, probability/statistics, and optimization theory. Ability to mathematically justify algorithmic choices.
• Hands-on Quantization Experience: Practical experience with PTQ/QAT workflows, low-precision arithmetic (int8, int4, fp8), and troubleshooting numerical instability in deep networks.
• Toolchain Familiarity: Experience with model formats (ONNX, PyTorch, TensorFlow) and graph-level optimizations.

Preferred Qualifications

• Experience with compiler infrastructure (MLIR, LLVM, TVM, Glow) and lowering high-level IR to hardware intrinsics.
• Research focus on "hardware-aware" neural network design or co-design.
• Experience implementing custom kernels or runtime support for NPUs/accelerators.
• Familiarity with firmware constraints in embedded systems.

What You Will Gain

• Be part of a pioneering team shaping the future of AI and edge computing.
• Work on innovative projects that solve real-world challenges.
• Opportunity to grow with a dynamic, forward-thinking company.
• Competitive salary, benefits, and a collaborative work environment.

#LI-FCC3