Staff Machine Learning Engineer, Voice AI

What this role involves

Together AI is building inference infrastructure for voice applications. This Staff ML Engineer role focuses on optimizing model serving for voice workloads, including speech-to-text and text-to-speech, using inference engines like TRT-LLM and SGLang. The role involves owning the voice inference roadmap, driving performance, building evaluation frameworks, and collaborating with model partners.

Skills this posting asks for

• trt-llm
• sglang
• whisper
• parakeet
• orpheus
• kokoro
• snac
• encodec
• streaming inference
• gpu optimization
• batching strategies
• memory management
• real-time audio
• latency optimization
• serverless endpoints
• dedicated endpoints
• evaluation frameworks
• wer
• tts
• stt
• speech-to-speech
• audio-native llms
• codec-based architectures
• model deployment

Requirements

• Level: staff

From the employer’s posting

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 speech-to-text and text-to-speech models with best-in-class latency and reli…