ML/AI Compiler Engineer
Core
Design and implement AI/ML compiler technologies to optimize models for embedded hardware, delivering high-performance inference across diverse semiconductor platforms.
Role type
Senior IC ML/AI Compiler Engineer
Builds
Compiler tools for ARM and RISC-V based CPU cores enabling pre-silicon and production software development for automotive SOCs
Domain
Embedded Systems / Automotive / Compiler Technology
Deliverable
production ML models
Required skills
C++ (production quality), Python, LLVM/MLIR, LLVM IR, Clang, LLVM Pass Framework, Optimization Pipelines, Code Generation, Linkers, Graph compiler passes optimization, Model lowering (PyTorch/TensorFlow), Graph-level optimizations (fusion, tiling, scheduling), Compiler code analysis, Computer architecture (caches, pipelines, ISAs), Embedded systems programming
Preferred skills
Experience with ML frameworks (PyTorch, TensorFlow, ONNX, XLA, TVM, TensorRT), Open-source community contribution
Technologies
LLVM, MLIR, C++, Python, PyTorch, TensorFlow, ONNX, XLA, TVM, TensorRT, ARM, RISC-V
Responsibilities
Design and implement AI/ML compiler technologies; Design and implement features for ARM and RISC-V CPU cores; Work with core architecture design teams and internal tool consumers; Contribute to design, development, and deployment cycles for NXP specific compiler features; Collaborate with hardware architects and ML researchers on model lowering and optimization.
Seniority
Senior, hands-on IC
