Lead AI Engineer - Conversational AI & LLM

Lead AI Engineer (Conversational AI & LLMs) Position Details : Location : Hyderabad (Development Centre) Work Mode : 5 Days WFO (Sunday & Monday week-off) Experience Required : 5 to 8 years Employment Type : Full-Time (Permanent) Notice Period : 0 to 15 Days (Immediate joiners highly preferred) About the Client : Our client is a well-established, US-headquartered enterprise product company with a multi-decade legacy in the communications technology space. They operate a rapidly expanding development center in Hyderabad and are currently scaling their operations targeting a 5-10x yearly growth trajectory. They offer a highly stable, product-driven engineering culture, robust employee benefits, comprehensive health insurance, and the opportunity to build cutting-edge tech from scratch. About the Role : We are seeking a highly skilled Lead AI Engineer to architect and build next-generation conversational AI, voice AI, and autonomous agent systems. In this role, you will spearhead the development of AI-powered enterprise applications using state-of-the-art Large Language Models (LLMs), real-time audio streaming, and Retrieval-Augmented Generation (RAG) pipelines. You will be responsible for optimizing models for latency, token efficiency, and accuracy while collaborating closely with cross-functional product and DevOps teams to integrate these solutions into core enterprise platforms. Key Responsibilities : - Design and develop highly scalable AI-powered enterprise applications using LLMs. - Build Voice AI solutions optimized for real-time, low-latency conversational systems. - Develop autonomous AI Agents capable of reasoning, planning, and executing complex tool-calling workflows. - Design, build, and implement highly efficient RAG pipelines utilizing advanced vector databases. - Integrate AI services seamlessly with REST APIs, WebSockets, SIP, and existing enterprise infrastructure. - Develop and maintain highly scalable backend microservices using Python. - Optimize all AI applications and workflows for latency, token cost reduction, and response accuracy. - Evaluate, benchmark, and integrate emerging AI frameworks and models into the production stack. Required Technical Expertise : - Programming & Backend : Expert-level proficiency in Python (Mandatory). Strong hands-on experience with FastAPI, Django, REST APIs, WebSockets, Asyncio, and Microservices architecture. - Large Language Models (LLMs) : Proven experience with OpenAI APIs, GPT-4o/GPT-5, and Claude. Deep understanding of Prompt Engineering, Function/Tool Calling, Structured Outputs, JSON Schema, Context Window Management, Token Optimization, and Model Evaluation. - Voice AI : Hands-on experience with Speech-to-Text (STT), Text-to-Speech (TTS), OpenAI Realtime API, Streaming Audio, Voice Activity Detection (VAD), and Realtime WebSocket APIs. - RAG & Databases : Strong experience building RAG systems utilizing Embeddings and Vector Databases (Redis, Pinecone, Weaviate, Qdrant, or Milvus). - AI Libraries & Frameworks : Proficiency with the OpenAI SDK, LangChain, LlamaIndex, Hugging Face Transformers, Sentence Transformers, and Pydantic AI. Preferred Qualifications (Good-to-Have) : - Strong domain experience in Conversational AI, Voice AI, AI Assistants, Customer Support Automation, or Workflow Automation. - Familiarity with JavaScript or TypeScript. - Hands-on experience with the Gemini ecosystem. - Knowledge of MCP (Model Context Protocol), AI Guardrails, Prompt Versioning, Cost Optimization strategies, and AI Evaluation Frameworks. Interview Process & Logistics : - Round 1 : Technical Coding Assessment - Round 2 : Technical Interview (Face-to-Face) - Round 3 : Techno-Managerial & HR Discussion - Office Timings : 10 : 00 AM to 7 : 00 PM .