Vai al contenuto
AI.info

jobs

Software Engineer - 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; Toronto; New York; Montreal; Seattle
Status
Open
Posted
2026-10-05 23:25 UTC

Baseten is hiring inference performance engineers to make demanding LLM workloads faster and cheaper. The work spans the inference engine and runtime: quantization, speculative decoding, KV-cache reuse, chunked prefill, request scheduling and cache-aware routing, plus profiling across kernels, batching and routing. Applicants need a computer science or related degree, Python or C++, familiarity with LLM optimization, PyTorch or TensorRT, and GPU architecture knowledge. Upstream contributions to vLLM, SGLang or TensorRT-LLM are welcome, not required. The role is hybrid across five North American cities.

Original job posting