Voice AI Engineer

We're looking for a Voice AI Engineer to build and own our real-time Voice AI stack end-to-end, from architecture and development to production deployment. You'll work on AI agents that listen, understand, and respond in real time, with a strong focus on latency, scalability, and reliability.

Responsibilities:

• Build and scale real-time voice AI agents and voice pipelines (STT, LLM TTS).
• Work with LiveKit Agents, Pipecat, or similar voice AI frameworks.
• Develop backend services using Python/Node.js, asyncio, WebSockets, WebRTC, and streaming APIs.
• Integrate STT, LLM, and TTS models/services.
• Optimize latency, concurrency, audio quality, and system reliability.
• Build integrations with telephony platforms and third-party APIs.
• Deploy, monitor, debug, and improve systems in production.
• Take end-to-end ownership of features and technical solutions.

Requirements:

• 2+ years of strong backend/software engineering experience.
• Hands-on experience building Voice AI, voice bots, conversational AI, or real-time audio systems.
• Experience with LiveKit, Pipecat, or similar frameworks.
• Strong Python and/or Node.js skills.
• Experience with async programming, WebSockets/WebRTC, streaming, and real-time systems.
• Experience integrating STT/TTS with LLMs.
• Strong understanding of production deployment, debugging, and performance optimization.