Lead Generative AI Engineer

Job Description - Lead Generative AI Engineer

Location: Hyderabad

Experience: 5 - 8 Years

Work Mode: 5 Days WFO

Notice Period: 0 - 15 Days

Employment: Full-Time

About the Role:

We are looking for a Lead Generative AI Engineer with strong hands-on experience in LLMs, Voice AI, RAG, AI Agents, and Python backend development to build scalable, real-time AI applications.

Key Responsibilities:

- Design and develop LLM-powered enterprise applications and AI Agents.

- Build real-time Voice AI solutions using STT, TTS, streaming audio and WebSockets.

- Develop RAG pipelines using embeddings and vector databases.

- Integrate OpenAI/Claude and other LLM APIs with enterprise applications.

- Build scalable Python microservices using FastAPI/Django.

- Implement tool/function calling, structured outputs and AI workflows.

- Optimize AI solutions for latency, cost and accuracy.

- Work with Product, QA and DevOps teams to deliver production-ready AI solutions.

Must-Have Skills :

- 5 - 8 years of relevant experience with strong Python development.

- Hands-on experience with OpenAI APIs, GPT-4o/GPT-5 or equivalent LLMs, and Claude.

- Strong experience in RAG, embeddings and Vector Databases.

- Experience with AI Agents, Function/Tool Calling and Prompt Engineering.

- Hands-on Voice AI experience: STT, TTS, OpenAI Realtime API, VAD and streaming audio.

- Strong knowledge of FastAPI/Django, REST APIs, WebSockets, asyncio and microservices.

- Experience with Redis and preferably Pinecone, Qdrant, Weaviate or Milvus.

- Experience with LangChain, LlamaIndex or OpenAI SDK.

Good to Have :

- MCP, AI Guardrails, AI Evaluation, Prompt Versioning and AI Cost Optimization.

Skills

Python, Generative AI, RAG, FastAPI, LangChain, Redis, Django