Jobs

Together AI is seeking a Staff Machine Learning Engineer to lead the model serving layer for its Voice AI platform. This foundational role involves optimizing inference for state-of-the-art voice models like Whisper and Parakeet, focusing on latency and throughput using engines like TRT-LLM and SGLang. The ideal candidate will have 8+ years of ML engineering experience with deep expertise in model serving, GPU optimization, and a strong background in speech and audio ML. You will own the voice inference roadmap, drive best-in-class performance, and shape the architecture for next-generation voice model support on a high-impact, early-stage team.