Lead AI Engineer - Generative AI & Agentic AI

We are seeking a Lead AI Engineer with 7 8 years of experience to design and lead the development of enterprise-scale Generative AI platforms and Agentic AI systems.

The ideal candidate will have strong expertise in LLM-based application development, multi-agent systems, RAG architectures, and scalable AI infrastructure. This role will drive the design and implementation of AI copilots, enterprise knowledge assistants, automation agents, and AI-driven workflows that integrate with enterprise systems and data platforms.

You will lead the architecture and development of production-grade AI solutions, mentor AI engineers, and define best practices for building scalable, reliable, and secure AI applications.

Key Responsibilities

• Design and architect enterprise Generative AI platforms and AI-powered applications
• Lead the development of AI copilots, enterprise assistants, and agent-based automation systems
• Design multi-agent architectures using modern agent frameworks
• Architect and implement RAG (Retrieval-Augmented Generation) platforms
• Build scalable LangChain / LlamaIndex / LangGraph orchestration pipelines
• Develop AI agents capable of reasoning, planning, and executing tasks
• Design AI microservices and APIs using Python-based frameworks
• Develop interactive AI tools and dashboards using Streamlit
• Integrate LLM APIs such as OpenAI, Azure OpenAI, Claude, Gemini, and open-source models
• Design vector search and semantic retrieval architectures
• Optimize prompt engineering strategies and LLM inference pipelines
• Work closely with MLOps teams to deploy, monitor, and scale AI services
• Define AI architecture standards, best practices, and governance
• Mentor and guide AI engineers and cross-functional teams
• Evaluate and adopt emerging GenAI and AI agent technologies

Must-Have Skills

• Expert Python programming for AI and backend systems
• Extensive experience building LLM-powered applications
• Strong expertise in LangChain, LlamaIndex, or similar AI frameworks
• Experience implementing RAG architectures
• Experience developing Streamlit applications
• Experience integrating LLM APIs
• Strong understanding of AI system architecture
• Experience designing microservices and API-based AI systems
• Experience with vector databases and semantic search
• Experience with Git-based development workflows

Good-to-Have Skills

Agentic AI Frameworks : LangGraph, CrewAI, Microsoft AutoGen

AI / GenAI Tools : Haystack, LangSmith, Guardrails AI

Vector Databases : pgvector, Pinecone, Chroma, FAISS