ML/AI Compiler Engineer

About the role

Join NXP's Global Compiler Team to develop cutting‑edge AI/ML compiler technologies for embedded processors. You will work on both proprietary and open‑source tools, enabling high‑performance inference on automotive and other semiconductor platforms.

Key responsibilities

• Design and implement AI/ML compiler technologies using C++ and LLVM to optimize models for embedded hardware.
• Develop features for ARM and RISC‑V CPU cores and integrate them into NXP's compiler framework.
• Collaborate with hardware architects, ML researchers, and core architecture teams to shape model lowering, optimization, and execution.
• Work with a worldwide development team on design, development, and deployment of NXP‑specific compiler features.

Required profile

• University degree in Computer Science or Computer Engineering with exposure to Machine Learning, Edge AI, and Embedded Systems.
• 5+ years of professional experience in compiler technologies (LLVM/MLIR, Clang, optimization pipelines, code generation, linkers).
• Strong knowledge of computer architecture, caches, pipelines, and instruction set architectures.
• Excellent communication skills and ability to work effectively in a global virtual environment.

Required skills

• C++ programming
• LLVM, MLIR, LLVM IR, Clang, LLVM Pass Framework
• Optimization pipelines, code generation, linkers
• Python programming
• ML frameworks: PyTorch, TensorFlow
• Software stack: ONNX, XLA, TVM, TensorRT
• Graph compiler passes, model lowering, fusion, tiling, scheduling
• Embedded systems programming and compiler requirements for embedded devices

What we offer

• Permanent full‑time contract with competitive salary, bonus plan, lunch vouchers and 25 vacation days.
• Opportunity to buy company shares at a 15% discount.
• Flexible work hours and work‑from‑home policy.
• Access to online and offline learning opportunities for professional development.
• Modern office in Bucharest with relaxation areas, library, cafeteria and restaurant.