Role Overview
We are looking for a highly skilled Full-Stack AI Engineer to build a real-time AI avatar platform that enables natural video conversations between users and AI-powered digital humans.
The ideal candidate should have experience with real-time audio/video streaming, LLM integration, speech processing, WebRTC, and modern full-stack development. This is not a simple chatbot project—it involves building a low-latency, production-ready conversational AI system.
---
Responsibilities
- Design and develop a real-time conversational AI platform.
- Build a browser-based video call interface.
- Integrate real-time Speech-to-Text (STT).
- Connect OpenAI GPT models for intelligent conversations.
- Integrate Text-to-Speech (TTS) services for streaming voice generation.
- Implement real-time AI avatar rendering using providers such as HeyGen Interactive Avatar, Simli, Tavus, or similar platforms.
- Build scalable backend APIs for conversation orchestration.
- Develop WebSocket/WebRTC pipelines for low-latency communication.
- Optimize end-to-end latency for natural conversations.
- Implement conversation memory and session management.
- Build authentication, user management, and analytics dashboards.
- Deploy and monitor production infrastructure.
Work Location: In person
