Principal AI Compiler Engineer (Relocation to Japan required)

This role is open across our global offices, and successful candidates may be based in any of our international office locations.

Key Responsibilities

• Develop and optimize compiler components for AI workloads (e.g., graph optimizations, operator fusion, scheduling).
• Collaborate with hardware and software teams to design compiler backends for NPUs, and custom accelerators.
• Implement performance tuning techniques for deep learning models across diverse architectures.
• Contribute to open-source compiler projects and maintain internal toolchains.
• Analyze and improve compilation pipelines for frameworks like PyTorch, TensorFlow, and ONNX.

Required Qualifications

Master’s degree or PhD in Computer Science, Electrical Engineering, or related field.

Strong proficiency in C++ , Python , and compiler design principles.

2 out of 3 below,

• Knowledge of AI frameworks (PyTorch, TensorFlow)
• Familiarity with hardware architectures (GPU, TPU, NPU) and parallel computing.
• Understanding of graph-based optimizations.

Preferred Qualifications

Experience with quantization , kernel optimization , and code generation for AI accelerators .

Experience with MLIR, LLVM, or similar compiler infrastructures.

Contributions to open-source compiler or AI projects.

Understanding of performance profiling and benchmarking for AI workloads.