Senior Machine Learning Engineer, Voice AI

📋 Description Own the model serving stack for STT, TTS, and speech-to-speech. Work with accelerators (H100/H200/B200) to optimize voice model inference. Collaborate with partners to productionize models on Together's infrastructure. Profile and debug the full inference stack to ship measurable improvements. Build evaluation frameworks guiding model selection and roadmap. Ensure serving layer meets latency and reliability for real-time voice APIs. 🎯 Requirements 5+ years of ML engineering focusing on model serving or ML infrastructure. Hands-on experience with LLM serving engines (vLLM, SGLang, TensorRT-LLM) and reading internals. Strong Python and PyTorch; GPU profiling/optimization (CUDA, memory, kernel debugging). Track record shipping ML systems to production with measurable gains. Strong product sense for voice app developers; fast-paced, small team. Bachelor's or Master's in CS/EE or related field, or equivalent experience. 🎁 Benefits Startup equity, health insurance, and other competitive benefits.