Not specified; not specified; competitive salary +...
Python and c/c++ systems programming
Pytorch and onnx framework experience
Post-training quantization (ptq) and qat
This role focuses on engineering core optimization technology to run state-of-the-art Generative AI and Vision-Language Models on NXP's next-generation edge platforms
Job Summary
This role focuses on engineering core optimization technology to run state-of-the-art Generative AI and Vision-Language Models on NXP's next-generation edge platforms.
The successful candidate will design scalable PTQ and QAT workflows while bridging the gap between abstract mathematical algorithms and physical hardware constraints.
Join a pioneering team that values every point of view and fosters innovation by defining how frontier AI models are executed on-device for fast, reliable, and power-efficient performance.
Matching Summary
This role focuses on engineering core optimization technology to run state-of-the-art Generative AI and Vision-Language Models on NXP's next-generation edge platforms.
Salary
Not specified; Not specified; Competitive salary and benefits mentioned
Skills & Requirements
Must-have
Python and C/C++ systems programming
PyTorch and ONNX framework experience
Post-Training Quantization (PTQ) and QAT
Generative AI and Transformer architectures
Memory management and hardware mapping
Nice-to-have
Experience with MLIR or TVM compilers
Knowledge of GPTQ and Smoothquant techniques
Familiarity with embedded system constraints
Hardware accelerator profiling experience
Proof-of-Concept evaluation skills
Key Requirements
MSc or Ph.D. in Computer Science, Electrical Engineering, or Mathematics
Specialization in Machine Learning or Deep Learning
Proven experience with CNN and Generative AI architectures