Jobs

Together AI is seeking a Senior ML Engineer to lead the model serving layer for their Voice AI platform, which powers real-time voice applications. This foundational role involves hands-on optimization of inference engines like TRT-LLM and SGLang for models such as Whisper and Parakeet, focusing on latency and throughput. The ideal candidate will have 5+ years of experience in ML engineering with a focus on model serving and a strong background in Python, PyTorch, and GPU optimization. You will shape how Together AI serves voice models, working with state-of-the-art accelerators and collaborating with model partners to bring cutting-edge voice AI to production.