> Markdown version of [/jobs/ext/4669144-performance-engineer](https://www.wearedevelopers.com/jobs/ext/4669144-performance-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Performance Engineer - **Company:** OMNIVA LLC - **Location:** Bellevue, WA, United States - **Experience:** Expert - **Salary:** $200,000 - $300,000 - **Contract:** Permanent contract - **Skills:** High Performance Computing, Large Language Models, SGLang, Free and Open-Source Software, Machine Learning Operations, TensorRT - **Published:** November 11, 2026 - **Apply:** https://www.thejobnetwork.com/job/487e4155-8e31-40fe-95cd-f8326d45df8f/performance-engineer ## About the Role * 4+ years for Senior, or 7+ years for Staff, in performance engineering, ML systems, HPC or inference infrastructure. Equivalent depth shown through open-source contributions, leaderboard results or published kernels counts too., * Production experience with at least one major LLM serving stack: vLLM, SGLang or TensorRT-LLM. You've shipped and tuned real deployments, well past the quickstart. \n * Strong GPU performance fundamentals: roofline analysis, memory-bound versus compute-bound reasoning, and profiling with Nsight, DCGM, Kineto or similar tools. You benchmark with statistical rigor and control for variance, warmup and clock effects.