Senior Software Engineer, Voice AI
Core
Design, build, and operate a production voice AI platform handling thousands of daily patient calls for automated test status, identity verification, and intelligent routing in the healthcare sector.
Role type
Senior Software Engineer, Voice AI
Builds
Natera's Voice AI platform (telephony, speech-to-text, LLM orchestration, text-to-speech) and agentic conversational workflows.
Domain
Healthcare / Voice AI / Conversational AI
Deliverable
production ML models | product features
Required skills
Voice AI pipeline architecture, multi-agent orchestration, real-time audio streaming, telephony integration, TypeScript/Node.js, LLM API integration, ASR/TTS optimization, latency management, WebSocket handling, analytics observability
Preferred skills
Healthcare/biotech domain experience, AWS infrastructure (ECS, Lambda, Bedrock), real-time systems expertise, RAG architectures, LLM observability tools
Technologies
Twilio, Deepgram, OpenAI, Anthropic, ElevenLabs, Azure Speech, NestJS, AWS, Kafka, Datadog
Responsibilities
Own end-to-end voice AI architecture from media streams to call disposition; Design and implement multi-agent systems with tool calling and state management; Build and optimize real-time audio pipelines (VAD, codecs, interruption handling); Architect analytics infrastructure for voice-specific metrics; Solve voice-specific challenges like turn-taking and barge-in; Integrate voice agents with internal services; Drive platform reliability and failover strategies; Mentor team members on voice AI best practices
Seniority
Senior, hands-on IC