Related skills
nestjs node.js twilio typescript websocket📋 Description
- Own end-to-end voice AI architecture - from telephony streams to call disposition.
- Design multi-agent orchestration and tool calling for patient workflows.
- Build real-time audio pipelines: WebSocket streaming, VAD, latency management.
- Architect analytics: per-segment latency, call efficacy, ASR error rates.
- Solve voice challenges: turn-taking, silence detection, barge-in, latency budgets.
- Integrate voice agents with internal services via secure authenticated APIs.
🎯 Requirements
- 5+ years software engineering, 2+ years building production voice AI.
- End-to-end voice AI pipelines: telephony through STT/LLM/TTS.
- Agentic architectures: multi-agent orchestration, tool calling, memory/state.
- Voice-specific challenges: VAD tuning, turn-taking, latency budgets.
- Telephony experience: Twilio media streams, SIP, IVR.
- TypeScript/Node.js with NestJS.
- STT/TTS providers: Deepgram, OpenAI, ElevenLabs, Azure.
- LLM APIs: OpenAI Real-time, Claude.
- Strong communication and high autonomy.
🎁 Benefits
- Competitive benefits: medical, dental, vision, life, disability plans.
- Free genetic testing and fertility care benefits for employees and dependents.
- Pregnancy/bonding leave, 401k, commuter benefits, generous referral program.
- Opportunities for growth and impact within a leading biotech company.
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!