Senior AI Inference Systems Engineer | GPU Kernels & Runtime

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

Job summary

NVIDIA in Santa Clara, CA is seeking outstanding AI systems engineers to advance the inference software stack. You will design and optimize kernels, build new abstractions for LLM serving engines, and contribute to accelerators and runtimes that power large language models and AI workloads.

You will collaborate across teams, work on CUDA C/C++, Triton, and cutting-edge MLIR-based tooling, and participate in open source projects.

Qualifications

• Masters degree in CS, EE, or related field; PhD preferred.
• 6+ years experience in ML/DL systems development (academic/industry).
• Strong experience with deep learning frameworks and inference engines.
• Strong Python and C/C++ programming skills.
• Experience in GPU kernel development and performance optimizations (CUDA, cuTile, Triton).

Responsibilities

• Innovating and developing AI systems technologies for efficient inference.
• Designing, implementing, and optimizing kernels for high impact AI workloads.
• Designing and implementing abstractions for LLM serving engines.
• Building JIT domain specific compilers and runtimes.
• Collaborating with NVIDIA teams across frameworks, libraries, kernels, and GPU arch teams.

Skills

Python

C/C++

GPU kernel development

ML/DL systems development

Deep learning frameworks experience

Education

Master's degree in CS/EE or related field

PhD preferred

Tools

CUDA C/C++

cuTile

Triton

PyTorch

JAX

TensorFlow

ONNX

Job description

NVIDIA in Santa Clara, CA is seeking outstanding AI systems engineers to advance the inference software stack. You will design and optimize kernels, build new abstractions for LLM serving engines, and contribute to accelerators and runtimes that power large language models and AI workloads.

You will collaborate across teams, work on CUDA C/C++, Triton, and cutting-edge MLIR-based tooling, and participate in open source projects.