jobs

Software Engineer - Model Products

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

Company

Baseten

Location

San Francisco; Toronto; New York; Montreal; Seattle

Status

Open

Posted

2025-10-11T03:41:17.218+00:00

Baseten is hiring a software engineer for its Model Performance team, working on the Model APIs surface — the hosted endpoints that serve open-source models. The work covers structured outputs, tool calling and multi-modal serving, plus profiling TensorRT-LLM and CUDA kernels, tuning memory and multi-GPU communication, and building benchmarks and API fundamentals like versioning, quotas and metering. The posting asks for three or more years with distributed systems or large-scale APIs and strong performance debugging instincts; prior ML experience is not required. The role is hybrid across five cities.