Senior HPC Performance Engineer — AI for Science (Equity)

NVIDIA Corporation; Santa Clara (CA); On-site; USD 184,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in Santa Clara is seeking a Sr. HPC Performance Engineer to design and optimize large-scale CUDA-backed ML training frameworks. You will work with a team advancing scientific ML across digital biology and beyond.

You will design high-performance features, port kernels to GPUs, and collaborate with HPC, AI infrastructure and research teams to drive testing and maintain algorithms and software modules.

Qualifications

• Advanced degree in a quantitative field (CS, physics, math, or related).
• 5+ years of relevant experience with performance engineering.
• Strong C++/Python and CUDA proficiency; kernel design experience.
• Experience with PyTorch, JAX, Warp frameworks and HPC for biology/chemistry.

Responsibilities

• Design and implement performant features for CUDA-backed ML training frameworks.
• Optimize kernel design, GPU porting, data structures, and distributed learning.
• Improve a wide range of ML models with accelerated hardware/software stacks.
• Collaborate with HPC, AI infrastructure and research teams; drive testing.

Skills

C++/Python parallel

CUDA

PyTorch/JAX/Warp

HPC for biology/chemistry

5+ years experience

Advanced degree

Software design/packaging

Leadership/self-direction

Communication skills

Team collaboration

Education

Advanced degree in a quantitative field

Tools

CUDA

Triton

Job description

NVIDIA in Santa Clara is seeking a Sr. HPC Performance Engineer to design and optimize large-scale CUDA-backed ML training frameworks. You will work with a team advancing scientific ML across digital biology and beyond.

You will design high-performance features, port kernels to GPUs, and collaborate with HPC, AI infrastructure and research teams to drive testing and maintain algorithms and software modules.