Lead AI Engineer - LLM/Voice AI

Role Overview :

Design and develop AI-powered enterprise applications using LLMs and Voice AI solutions for real-time conversational systems.

Technical Stack :

- Programming: Python (Mandatory), JavaScript/TypeScript (Preferred)

- Backend: FastAPI, Django, REST APIs, WebSockets, Async Programming (asyncio), Microservices, Redis

- LLMs: OpenAI APIs, GPT-4o, Claude, Gemini, Prompt Engineering, Function Calling, Structured Outputs, Context Window Management, Token Optimization, AI Safety, Model Evaluation

- Voice AI: STT, TTS, OpenAI Realtime API, Streaming Audio, VAD, Realtime WebSocket APIs

- RAG: Embeddings, Vector Databases (Redis, Pinecone, Weaviate, Qdrant, Milvus)

- AI Libraries: OpenAI SDK, LangChain, LlamaIndex, Hugging Face Transformers, Sentence Transformers, Pydantic AI

Roles & Responsibilities :

- Design and implement RAG pipelines using vector databases.

- Develop AI Agents capable of reasoning, planning, and tool execution.

- Integrate AI services with REST APIs, WebSockets, SIP, and enterprise systems.

- Develop scalable Python microservices.

- Optimize AI applications for latency, cost, and accuracy.

- Build reusable AI workflows and tool-calling frameworks.

- Collaborate with Product, QA, and DevOps teams.

Good to have :

- MCP (Model Context Protocol), AI Guardrails, Prompt Versioning, Cost Optimization, AI Evaluation Frameworks.