Senior Software Engineer, Voice AI

This is a fully remote position, open to applicants in United States.

📋 Description

• Take ownership of the complete voice AI architecture — spanning Twilio media streams, LLM orchestration, TTS output, and call disposition.

• Create and implement multi-agent systems utilizing tool calling, agent transitions, and shared conversation state to support intricate patient workflows.

• Develop and enhance real-time audio pipelines — including WebSocket streaming, codec management (mulaw/PCM), VAD configuration, and interruption handling.

• Design analytics and observability infrastructure focused on voice-specific metrics: per-segment latency (STT/LLM/TTS), call effectiveness, disposition accuracy, and ASR error rates.

• Address voice-specific issues such as turn-taking timing, silence detection thresholds, barge-in recovery, medical term recognition, and end-to-end latency optimization.

• Connect voice agents with internal services through secure authenticated APIs.

• Enhance platform reliability by eliminating single points of failure, implementing multi-provider LLM failover, and designing paths for graceful degradation.

• Collaborate with product and clinical operations teams to enhance self-service efficacy rates and decrease call escalations.

• Mentor team members on best practices in voice AI and contribute to architectural decision-making.

⛳️ Requirements

• Over 5 years of software engineering experience, with a minimum of 2 years dedicated to developing production voice AI or conversational AI systems.

• Profound experience with voice AI pipelines — understanding the complete flow from telephony through STT, LLM processing, TTS, and back to the caller, including real problem-solving at each stage.

• Production experience with agentic architectures — including multi-agent orchestration, tool calling, agent handoffs, memory/state management, and LLM-driven decision-making in real-time conversational contexts.

• Strong grasp of voice-specific challenges: VAD tuning, turn-taking, interruption/barge-in handling, latency budgets, audio codec management, and the distinctions between voice and text-based AI user experiences.

• Practical experience with telephony systems — such as Twilio (media streams, SIP, IVR), or comparable platforms with WebSocket-based audio streaming.

• Proficiency in TypeScript/Node.js with robust async programming patterns; experience with NestJS or similar frameworks.

• Familiarity with STT/TTS providers (Deepgram, OpenAI, ElevenLabs, Azure Speech) and an understanding of ASR accuracy challenges (domain-specific vocabulary, noise handling).

• Production experience with LLM APIs — including OpenAI (particularly the Realtime API), Anthropic Claude, or similar; expertise in prompt engineering for conversational agents.

• High level of agency and autonomy — proactively seeking out impactful work without waiting for permission, detailed specifications, or guidance. You take initiative and drive projects to completion.

• Excellent communication skills — capable of translating complex voice AI architecture choices for product and clinical stakeholders.

🏝️ Benefits

• Comprehensive medical, dental, vision, life, and disability plans available for eligible employees and their dependents.

• Complimentary testing for Natera employees and their immediate family members.

• Fertility care benefits.

• Leave for pregnancy and baby bonding.

• 401k benefits.

• Commuter benefits.

• Generous employee referral program!