ML/AI Junior Compiler Engineer

About the role

Join NXP's Global Compiler Team to develop AI/ML compiler technologies for embedded processors. You will work on optimizing models for automotive SOCs using C++ and LLVM, contributing to high‑performance inference across semiconductor platforms.

Key responsibilities

• Design and implement AI/ML compiler technologies, optimizing models for embedded hardware with C++ and LLVM.
• Develop compiler features for ARM and RISC‑V CPU cores and collaborate with core architecture teams.
• Work with worldwide development teams to design, develop, and deploy NXP‑specific compiler features.

Required profile

• University degree in Computer Science or Computer Engineering with exposure to Machine Learning, Edge AI, and Embedded Systems.
• At least 1 year of professional experience with compiler technologies (LLVM/MLIR, LLVM IR, Clang, LLVM Pass Framework, optimization pipelines, code generation, linkers).
• Experience with ML frameworks (e.g., PyTorch, TensorFlow) and related software stacks (ONNX, MLIR, XLA, TVM, TensorRT).

Required skills

• Programming in C++ and Python.
• LLVM, MLIR, LLVM IR, Clang, LLVM Pass Framework.
• Optimization pipelines, code generation, linkers.
• Knowledge of graph compiler passes, model lowering, and graph‑level optimizations (fusion, tiling, scheduling).
• Embedded systems programming and familiarity with ARM and RISC‑V architectures.

What we offer

• Permanent full‑time contract with competitive salary, bonus plan, lunch vouchers, 25 vacation days, and discounted company shares.
• Flexible working hours, work‑from‑home policy, and a modern office in Bucharest with relaxation areas, library, cafeteria, and nearby public transport.
• Professional development through online and offline learning opportunities.
• Social activities, free coffee, fresh fruit days, and community initiatives.