jobs

Software Engineer - GPU Networking & Distributed Systems

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

2026-02-23T20:22:25.126+00:00

Baseten is hiring a software engineer to build the networking layer beneath its distributed LLM inference stack: integrating RDMA, RoCE and InfiniBand rather than TCP/IP, tuning communication for disaggregated KV cache offload and wide expert parallelism, cutting trillion-parameter model cold starts below ten seconds, validating throughput on H100 and Blackwell clusters, and writing communication kernels with NCCL and NVSHMEM. The posting asks for deep high-performance networking experience, C++ or Python, and NVIDIA memory-hierarchy knowledge. Hybrid, across five listed cities.