Software Engineer (Voice AI)

Moglix · Noida

Source and collection record

Last observed by our collector: 8 October 2026 at 11:46 pm IST. This is not a manual review or a confirmation from the employer.

Employer requisition: 4515

Job type and experience labels are automated discovery categories. The employer determines eligibility. Original experience wording was not retained separately; check the current employer page.

How sourcing and classification work · Report a discrepancy

Your application evidence checklist

Mark the statements you can support after reading the employer source. This checklist stays on this page; it does not score your eligibility or submit an application.

Attendance and availability: I checked the employer page for work location, office attendance, start date and duration.Current requisition: I checked the current employer requisition and its application requirements.

0 of 2 checks marked. Keep unresolved requirements as questions for the employer.

Collected role description

Roles & Responsibilities Strong Python development skills Experience with LLMs — OpenAI / Gemini / Claude or similar Understanding of prompt engineering and LLM-based application development Experience building AI agents / conversational AI Understanding of RAG, embeddings, vector databases and knowledge retrieval Experience with Speech-to-Text (STT) — Whisper, Deepgram, Google Speech, Azure Speech, etc. Experience with Text-to-Speech (TTS) — ElevenLabs, Azure, Google, Cartesia, etc. Understanding of real-time audio/voice pipelines Experience with WebSockets / streaming APIs Backend development using FastAPI / Flask Good understanding of REST APIs, JSON, authentication and async programming Experience integrating third-party APIs and AI services Basic knowledge of databases — PostgreSQL / MongoDB / Redis Good to Have Experience with Twilio / SIP / telephony APIs Experience building phone-call based voice agents Familiarity with VAD (Voice Activity Detection), interruption/barge-in and turn detection Understanding of latency optimization in real-time voice systems Experience with LangChain / LangGraph similar agent frameworks Docker and basic cloud deployment — AWS/GCP/Azure Basic understanding of observability, logging and tracing for AI applications Key Skills: Python, LLMs, AI Agents, Prompt Engineering, Speech-to-Text (STT), Text-to-Speech (TTS), Real-Time Audio Streaming, WebSockets, FastAPI, REST APIs, RAG, Vector Databases, Redis/PostgreSQL, Docker, and cloud deployment. Experience with Twilio/SIP, telephony integrations, LangGraph/LangChain, VAD, turn detection and real-time voice-agent optimization will be an added advantage. The ideal candidate should demonstrate that they can build this pipeline: User speaks → STT → LLM/Agent → tool/API calls → response → TTS → user hears response And preferably handle: interruptions + streaming + conversation memory + tool calling + low latency + failure handling.

Collected experience requirement

1-2 Years