Job Title

We are building next-generationAI Voice Agents for recruiters . You’ll design and implement real-time, low-latency conversational systems that combineLLMs, STT, TTS, RAG , and streaming pipelines. The backend runs inPython , with aReact/Node.jsfrontend. If you have built real-time voice systems that can handle human interruptions and dynamic context, this role fits you. Key Responsibilities Build and optimizereal-time AI Voice Agentsin Python. IntegrateTTS (e.g., ElevenLabs)andSTT (e.g., Deepgram)systems for natural, fast voice interaction. ImplementLLM integrationwith focus onlatency reductionandinterruption handling . Develop caching layers forprompts and audio streamsto reduce cost and delay. Design and maintainSIP, WebRTC, and WebSocketpipelines for call handling. Handleautomatic answering machine detection (AMD)and dynamic call routing. Work with React/Node.js frontend teams for end-to-end real-time communication. Required Skills Python : Strong backend development experience. Real-Time AI Voice Systems : Proven working experience ismandatory . LLM Integration : Deep understanding of latency, interruption handling, and RAG pipelines. Networking Protocols : Hands-on experience withSIP, WebRTC, and WebSockets . Frontend Collaboration : Working knowledge ofReactandNode.js . Preferred Skills Experience withElevenLabs ,Deepgram , or other leading TTS/STT APIs. Knowledge ofaudio stream caching , buffering, and GPU optimization. Familiarity withFreeSWITCH ,Asterisk , or similar VoIP platforms. Background inautomatic machine detectionand call classification. Why Join Us You’ll work on cutting-edgevoice-first AI infrastructureused by staffing companies worldwide. Early-stage team, fast decisions, deep tech stack, and clear impact.Salary is in INR