jobs
Software Engineer - GPU Kernels
ABOUT BASETENBaseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless dev
In inglese
- Company
- Baseten
- Location
- San Francisco; Toronto; New York; Montreal; Seattle
- Status
- Open
- Posted
- 2025-07-17T22:46:46.595+00:00
Baseten is hiring a GPU kernel engineer for its Model Performance team, working on its inference stack and embeddings inference. The work covers writing CUDA and PTX kernels for matrix multiplication, attention and mixture-of-experts routing, plus quantization, sparsity and compute/communication overlap, profiled with Nsight Systems, Nsight Compute and Torch Profiler. The posting asks for C++, GPU architecture knowledge and profiling experience; Cutlass, Triton, Flash Attention and open-source contributions help. Hybrid across five North American cities.
Original job posting