Full-Stack AI Engineer (Real-Time Conversational AI)

We are seeking a Full-Stack AI Engineer to build a low-latency, browser-based conversational AI avatar platform. The role involves developing real-time voice/video interactions, integrating LLMs, speech processing, AI avatars, and scalable backend services. You will design production-ready systems with seamless audio/video streaming, conversation memory, authentication, and cloud deployment.

Key Skills:

• Frontend: React.js, Next.js, TypeScript, Tailwind CSS
• Backend: Node.js, Express/NestJS, REST APIs, WebSockets, Redis, PostgreSQL/MongoDB
• AI/LLM: OpenAI API, Prompt Engineering, Function Calling, Conversation Memory
• Speech: Deepgram, Whisper, AssemblyAI, ElevenLabs/OpenAI TTS
• Real-Time: WebRTC, WebSockets, Live Media Streaming, Low-Latency Systems
• Avatar APIs: HeyGen, Simli, Tavus, D-ID (or similar)
• Cloud & DevOps: AWS/GCP/Azure, Docker, Kubernetes, CI/CD

Preferred: Python, FastAPI, LangChain/LangGraph, Vector Databases, LiveKit, Agora, Twilio Video.

Pay: ₹40,000.00 - ₹50,000.00 per month

Benefits:

• Cell phone reimbursement
• Paid sick time
• Paid time off

Work Location: In person

Skills

• LLMs
• React.js
• Next.js
• TypeScript
• Tailwind CSS