Senior Inference Engineer: AI-Driven GPU Kernel Optimization

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

Job summary

NVIDIA Corporation in Santa Clara, CA, seeks a Sr. Inference Engineer to accelerate LLM inference through GPU kernel optimization. You will lead kernel benchmarking, model-level performance analysis, and AI-driven optimization workflows across silicon and software stacks.

The role requires strong Python and C++, hands-on GPU profiling (CUPTI/NSYS/NCU), and experience with TRT-LLM, SGLang, or vLLM. Collaboration with compiler, hardware, kernel, and framework teams is essential to deliver

Qualifications

• Master's or PhD in CS/CE or equivalent experience.
• 6+ years of relevant industry experience.
• Experience building or directing agentic AI systems—code generation, automated optimization, or multi-step reasoning workflows.
• Strong Python and C++ skills with proven software engineering fundamentals.
• Hands-on GPU profiling with CUPTI, NSYS, and NCU.
• Direct experience with LLM inference frameworks such as TRT-LLM, SGLang, or vLLM.
• Working knowledge of GPU kernel optimization — CUDA, CUTLASS, Triton, or equivalent.

Responsibilities

• Drive GPU kernel microbenchmarking across configurations with real-silicon fidelity.
• Perform end-to-end model performance analysis for production inference deployments.
• Develop agentic kernel optimization using AI-driven analysis and silicon-verified validation.
• Collaborate with compiler, hardware, kernel, and framework teams to deliver production-grade gains.

Skills

Python

C++

Kernel optimization

Agentic AI systems

Multi-step reasoning workflows

Education

Master's or PhD in Computer Science or Computer Engineering

Tools

CUPTI

NSYS

NCU

TRT-LLM

SGLang

vLLM

CUDA

CUTLASS

Triton

Job description

NVIDIA Corporation in Santa Clara, CA, seeks a Sr. Inference Engineer to accelerate LLM inference through GPU kernel optimization. You will lead kernel benchmarking, model-level performance analysis, and AI-driven optimization workflows across silicon and software stacks.

The role requires strong Python and C++, hands-on GPU profiling (CUPTI/NSYS/NCU), and experience with TRT-LLM, SGLang, or vLLM. Collaboration with compiler, hardware, kernel, and framework teams is essential to deliver