Senior Inference Engineer, GPU Kernel Optimization

What you'll do

• Develop and maintain silicon-measured kernel benchmarking infrastructure for production LLM deployments.
• Analyze end-to-end model performance to identify high-value optimization opportunities and production policies.
• Build agentic AI systems to automate the diagnosis and exploration of GPU kernel performance gaps.
• Profile GPU performance using tools like CUPTI, NSYS, and NCU to attribute execution bottlenecks.
• Optimize GPU kernels using CUDA, CUTLASS, or Triton while analyzing PTX and SASS output.
• Collaborate with compiler, hardware, and framework teams to deliver upstream performance improvements.
• Validate kernel optimizations through rigorous silicon measurements and performance projection tooling.

What we're looking 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 for code generation, automated optimization, or multi-step reasoning workflows.
• Strong Python and C++ skills with proven software engineering fundamentals.
• Hands-on GPU profiling experience with CUPTI, NSYS, and NCU to attribute bottlenecks across kernel execution, compiler decisions, and runtime scheduling.
• Direct experience with LLM inference frameworks such as TRT-LLM, SGLang, or vLLM.
• Working knowledge of GPU kernel optimization using CUDA, CUTLASS, Triton, or equivalent, including the ability to read PTX or SASS output.
• Deep knowledge of SASS/PTX-level kernel analysis, compiler middle-end optimization, or GPU code generation pipelines (preferred).