Full Stack Engineer - Voice AI
Core
Building server-side infrastructure for real-time, low-latency conversational AI voice agents and voicebots.
Role type
Senior Full Stack Engineer (Voice AI)
Builds
Production-grade voice agents, real-time audio pipelines, and LLM orchestration systems.
Domain
Real-time systems, Conversational AI, Voice Interfaces
Deliverable
production ML models | product features
Required skills
Backend engineering, Voice AI/voicebot system development, Real-time audio streaming, LLM orchestration, Prompt engineering, Python, Cloud infrastructure (AWS/GCP/Azure), CI/CD, Observability
Preferred skills
LLM frameworks (LangChain, LlamaIndex), AI agent frameworks (LiveKit Agents SDK, Pipecat), Telephony APIs (Twilio, Plivo), ASR/TTS integration, Open-source contributions
Technologies
LiveKit, WebRTC, Python, Node.js, Docker, Kubernetes, AWS, GCP, PostgreSQL, Redis, OpenAI, Anthropic, Deepgram, Whisper, ElevenLabs
Responsibilities
Design and iterate on voice AI agents for real-time conversations; Integrate and orchestrate LLMs as reasoning backbone; Manage real-time audio/media streams; Write and refine prompts for agent behavior; Build backend services connecting telephony/audio infra to business logic; Maintain cloud infrastructure and observability; Instrument systems for latency and SLAs.
Seniority
Mid-Senior, hands-on IC