onsite
Senior Machine Learning Compiler Engineer - NVIDIA
ML Engineer
Lead the design and implementation of high‑performance machine learning compilers, integrating with NVIDIA's GPU stack and advancing AI system efficiency using C++, CUDA, and LLVM technologies.
About the role
Key Responsibilities
- Architect, develop, and optimize machine learning compiler components that target NVIDIA GPUs.
- Collaborate with hardware, driver, and software teams to ensure seamless integration with the broader AI stack.
- Design and implement code generation, optimization passes, and runtime support using LLVM and CUDA.
- Evaluate emerging ML frameworks and incorporate new features to improve performance and scalability.
- Mentor junior engineers and contribute to technical roadmaps for next‑generation AI compilers.
Requirements
- 5+ years of experience in systems programming with strong C++ and Python skills.
- Deep understanding of compiler theory, LLVM infrastructure, and GPU architectures.
- Hands‑on experience with CUDA development and performance tuning on NVIDIA GPUs.
- Proven track record of building or contributing to ML/DL compiler projects or similar high‑performance computing tools.
- Excellent problem‑solving abilities and ability to work cross‑functionally in a fast‑paced environment.
Skills
cpythoncudamachine learning