> Markdown version of [/jobs/ext/4787677-performance-engineer](https://www.wearedevelopers.com/jobs/ext/4787677-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:** Darwin - **Location:** San Francisco, CA, United States - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, C++ (Programming Language), Profiling, Nvidia CUDA, Computer Programming, Computer Engineering, Software Engineering, Graphics Processing Unit (GPU), Parallel Computation, ROCm - **Published:** November 19, 2026 - **Apply:** https://www.careerbuilder.com/job-details/performance-engineer-san-francisco-ca--58214da5-6a48-42f5-b1b4-cba9173db1d1 ## About the Role Performance Engineering, Artificial Intelligence (AI), Computer Engineering, Organizational Skills, Benchmarking, GPU (Graphics Processing Unit), Software Engineering, Memory Hardware, Computer Architecture, Kernel Programming, * Strong C++ and low level optimization experience (CUDA or similar) * Knowledge of memory hierarchies, parallelism and profiling * A record of measurable speed ups Nice to have * Non Nvidia target experience (ROCm or custom ISA) * GEMM and attention kernel work * Assembly or intrinsics ## Description The role: You will own the low level kernels that determine how quickly customer models run on the chip. There is no mature kernel library to lean on, so you will build it: matrix multiplies, attention, normalization and the operators that follow, tuned for a new memory and compute architecture., Why join: Your kernels set the performance customers see, and you will work next to the people designing the chip.