Software Engineer - Voice AI (Inference Runtime)

About this role

Baseten seeks a Software Engineer to own the Voice AI inference runtime stack, building production-grade systems for speech-to-text, text-to-speech, and voice agent workloads. You'll lead product areas end-to-end, optimize model serving for latency and throughput, and collaborate across teams to enable real-time voice AI at scale.

What you'll do

• Own Voice AI product areas end-to-end from architecture through implementation, rollout, and production operations
• Design and operate real-time, large-scale model serving systems for STT, TTS, and voice agent workloads
• Optimize inference stack for latency (p95/p99), throughput, and GPU efficiency through profiling and tuning
• Build infrastructure for multi-model voice agents with streaming I/O orchestration across components
• Drive cross-team collaboration on full-stack technical problems and coordinate delivery
• Mentor teammates through code reviews, design docs, and technical leadership

What they're looking for

• Production systems design and ownership with focus on tail latency optimization
• Python and general software engineering proficiency
• Real-time, large-scale distributed systems
• Machine learning infrastructure and model serving
• AI coding assistants (Claude, Cursor, Codex) for productivity
• Collaboration and cross-functional communication
• Model runtime optimizations (dynamic batching, scheduling, decode optimization)
• Containerization, orchestration, or distributed scheduling (Docker, Kubernetes)