Skip to content
AI.info

jobs

Staff Machine Learning Engineer, Voice AI

About the Role Together AI is building the best inference infrastructure for voice applications. Our Voice AI platform powers production-grade, real-time voice agents and applications — serving…

Company
Together AI
Location
San Francisco
Status
Closed
Posted
2026-05-19 18:19 UTC

Together AI is hiring a Staff ML Engineer to own the model serving stack behind its real-time voice platform. The work covers STT, TTS and speech-to-speech models: tuning inference engines such as TensorRT-LLM and SGLang, profiling GPU use on H100/H200/B200 hardware, designing batching for streaming audio, building evaluation frameworks, and integrating partner models. The posting asks for 8+ years of ML engineering, deep LLM serving engine experience, Python and PyTorch with CUDA-level optimisation, and speech/audio ML knowledge. It is a foundational, early-stage hire in San Francisco.

Original job posting