Job Information
| Location: | US (California) |
|---|---|
| Published: | Jul 15, 2026 |
| Employment Type: | Full Time |
| Salary: | 242k/yr |
Requirements: CUDA, Kernel optimization, GPU architecture, Tensor cores, C++, Python, Nsight Compute/Systems, Model-serving stacks (vLLM, TensorRT-LLM, llm-d, SGLang), Triton, Mojo, CuTe DSL, JAX, HIP / ROCm, NCCL, Kubernetes, Slurm, MLPerf benchmarking, Contributions to OSS (e.g., vLLM, SGLang, PyTorch, Triton, CUTLASS), Performance profiling and microbenchmarking