Description
Baseten is hiring a Voice AI Infrastructure Engineer to own the company’s in-house inference stack for Voice AI models. The role leads architecture, system design, implementation, rollout, and production operations for real-time, large-scale model-serving systems supporting STT, TTS, and voice-agent workloads. Responsibilities include optimizing latency, throughput, and GPU efficiency, building streaming infrastructure, coordinating with engineering teams, and mentoring teammates. The role requires a bachelor’s degree or higher in computer science or a related field, experience owning production-grade real-time systems, strong coding ability, and interest in ML/AI infrastructure.
