NVIDIA
Senior Inference Engineer, GPU Kernel Optimization
$184K–$288K
US, CA, Santa Clara +3 · Senior · Full-time · Posted Jul 27, 2026
- Location
- US, CA, Santa Clara
US, TX, Austin
US, NY, New York
US, WA, Seattle - Experience
- 6+ years of relevant industry experience.
- Education
- Master's or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience.
About the job
Optimizes NVIDIA’s LLM inference stack by building GPU kernel benchmarks, analyzing end-to-end model performance, and developing agentic systems for kernel optimization.
What you'll do
- Build silicon-faithful GPU kernel microbenchmarking across production configurations.
- Analyze model-level performance and serving economics to identify optimization opportunities and create production inference policies.
- Use AI-driven analysis to diagnose and optimize GPU kernels, validate results with silicon measurements, and collaborate across engineering teams.
What they ask for
- Master’s or PhD in Computer Science, Computer Engineering, or a related field, or equivalent experience.
- 6+ years of relevant industry experience.
- Experience building or directing agentic AI systems; strong Python and C++ skills.
- Hands-on GPU profiling with CUPTI, NSYS, and NCU; experience with LLM inference frameworks and GPU kernel optimization, including reading PTX or SASS.
Nice to have
- Deep knowledge of SASS/PTX analysis, compiler optimization, or GPU code generation pipelines.
- End-to-end agentic systems shipping experience or open-source contributions to LLM inference or GPU kernel libraries.
Pay
184,000 USD - 287,500 USD base salary
Tools
Python, C++, CUPTI, NSYS, NCU, TRT-LLM, SGLang, vLLM
AI focus
Build and apply agentic AI systems for code generation, automated optimization, and multi-step analysis of GPU kernels.
Model-written summary · the original posting is authoritative