Staff Machine Learning Engineer, Voice AI

Role

The role involves driving the model serving layer for voice workloads, optimizing inference engines like TRT-LLM and SGLang for models such as Whisper and Parakeet. Candidates must have 8+ years of ML engineering experience, deep expertise in LLM serving engines, and strong proficiency in Python, PyTorch, and GPU optimization.

Location: San Francisco
Employment: full time
Work pattern: unspecified
Seniority: senior

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Greenhouse feed. Source update: 2026-09-23T12:49:24-04:00. Check the employer’s page for the complete description, current availability and application terms.

• job-boards.greenhouse.io/togetherai/jobs/5140763007 ↗

Together AI RESEARCH PROFILE ↗