Senior Performance Compiler Engineer - Triton

About the role

The Senior Performance Compiler Engineer will play a pivotal role in advancing AI performance on NVIDIA GPUs through innovative compiler technology. This position leverages the latest GPU hardware and programming models to optimize complex AI algorithms and numerical methods.

Responsibilities

• Investigate NVIDIA GPU hardware architecture and programming models to identify new optimization opportunities.
• Work on advanced AI algorithms and numerics to enhance compiler optimizations.
• Design and implement compiler technology using MLIR to generate efficient, low-level GPU code from high-level kernel descriptions.
• Collaborate with hardware architects and the CUDA compiler team to ensure optimal product performance.

Requirements

• Bachelor, Masters or Ph.D. degree or equivalent experience in Computer Science, Computer Engineering, Applied Math, or a related field.
• 8+ years of relevant industry experience in software development.
• Strong C++ programming and software design skills, with a focus on performance analysis and debugging.
• Experience in parallel programming, including CUDA/OpenCL GPU programming or other models like OpenMP.
• Solid understanding of computer architecture and hands-on assembly-level programming experience.

Qualifications

• Experience in tuning BLAS or deep learning library kernels.
• Background in numerics and linear algebra.
• Experience with machine learning compilers like TVM or MLIR.
• Contributions to open-source projects, especially in the AI/ML or compiler space.
• Familiarity with the latest research in AI algorithms and numerics.

Skills

• Expertise in C++ and parallel programming.
• Knowledge of MLIR and GPU architectures.
• Experience with AI algorithms and numerical methods.
• Ability to debug and analyze performance issues.

Benefits

Competitive salaries, generous benefits package, and opportunities for equity. Applications are accepted until May 12, 2026.