jobs
Engineering Manager, Inference Performance
ABOUT BASETEN Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer.
In inglese
- Company
- Baseten
- Location
- San Francisco; New York
- Status
- Open
- Posted
- 2026-10-07 00:57 UTC
Baseten is hiring an engineering manager to lead part of its Inference Performance team, which makes demanding AI workloads run faster on GPUs. The manager hires and mentors inference performance engineers while staying close to the technical work: reviewing designs, guiding profiling, and productionizing quantization, speculative decoding, KV-cache reuse, chunked prefill and custom scheduling. Requirements include experience managing engineers, a GPU optimization background, and familiarity with PyTorch or TensorRT-LLM. The hybrid role spans San Francisco and New York; success is measured in tokens per GPU-hour, latency and cost.
Original job posting