NVIDIA is seeking a Sr. Inference Engineer to push GPU kernel optimization for LLM inference. The role focuses on silicon-measured kernel benchmarking, model-level performance projection, and agentic optimization systems that improve kernels at the assembly level.
You will collaborate with compiler, hardware, kernel, and framework teams to surface bottlenecks and deliver production-grade performance gains, with a base salary range clearly stated in the posting.
#J-18808-Ljbffr