Fathom is seeking a Model Performance Engineer to own the speed, cost, and reliability of our model inference stack and to build the fine‑tuning infrastructure that accelerates the AI team. You will optimize real systems serving millions of meetings with quantization, speculative decoding, and GPU selection.
This is a fully remote role with a fast-moving startup culture. You’ll own two main areas: inference performance and fine‑tuning pipelines, shipping production configurations and repeatable
#J-18808-Ljbffr