Key Responsibilities :
- Design and develop an AI human avatar that can act as a live meeting moderator
- Integrate the avatar into WebRTC-based video conferencing systems
- Build real-time pipelines for speech generation, lip-sync, and facial animation
- Enable the avatar to listen, interpret, and respond using conversational AI
- Implement moderation behaviors (greeting participants, asking questions, guiding discussion, handling Q&A)
- Stream avatar-generated video and audio into meetings via custom WebRTC media tracks
- Ensure low-latency performance for natural interactions
- Develop signaling and session control mechanisms using WebSockets or similar technologies
- Work with AI teams to incorporate voice tone, emotion modeling, and contextual awareness
- Optimize network performance (bitrate adaptation, jitter handling, packet loss recovery)
- Ensure privacy, security, and compliance in real-time communications
Required Technical Skills :
WebRTC & Real-Time Communication :
- Strong hands-on experience with WebRTC APIs (RTCPeerConnection, MediaStream, RTCDataChannel)
- Understanding of SDP negotiation, ICE, STUN, TURN servers
- Experience injecting synthetic audio/video streams into WebRTC sessions
- Knowledge of media codecs (Opus, VP8/VP9, H.264)
AI & Conversational Systems :
- Experience integrating LLMs or conversational AI for real-time dialogue
- Knowledge of Text-to-Speech (TTS) and Speech-to-Text (STT) systems
- Familiarity with dialogue orchestration and response timing
- Understanding of emotion-aware or context-aware AI systems (preferred)
Avatar Animation & Rendering :
- Experience with facial animation, lip-sync, or digital human rendering
- Familiarity with WebGL / Three.js / Unity / Unreal Engine or similar technologies
- Understanding of audio-driven facial animation pipelines
Frontend Development :
- Strong JavaScript / TypeScript skills
- Experience with React or other modern frontend frameworks
- Web Audio API and MediaStream handling
Backend / Signaling :
- Experience building real-time signaling servers using Node.js, Python (FastAPI), or similar
- Knowledge of WebSocket-based communication
- Experience with session orchestration and state management
Other Skills :
- Experience with real-time media servers like LiveKit, Mediasoup, Janus, or Kurento
- Background in virtual production, gaming, or character animation
- Knowledge of low-latency streaming optimization techniques
- Familiarity with AI moderation logic (detecting silence, interruptions, engagement levels)
- Exposure to multilingual voice systems