Role: AI Lead Engineer - Generative AI & LLM Applications

• Design and implement enterprise-grade GenAI solutions using LLMs (GPT, Claude, Llama and similar families).

• Build and optimize production-ready RAG pipelines including chunking, embeddings, retrieval tuning, query rewriting, and prompt optimization.

• Develop single- and multi-agent systems using LangChain, LangGraph, LlamaIndex and similar orchestration frameworks.

• Design agentic systems with robust tool calling, memory management, and reasoning patterns.

• Author MCP (Model Context Protocol) servers, tools, and resources, and integrate them with Cursor, Claude, Codex, Copilot, and internal enterprise systems.

• Build plugins and extensions for Claude, Codex, Cursor and GitHub Copilot ecosystems.

• Building AI Agents and Sub-Agents, Agent Skills for tools like Claude Code, Codex, and GitHub Copilot.

• Build scalable Python + FastAPI/Flask or MCP microservices for AI-powered applications, including integration with enterprise APIs.

• Implement model evaluation frameworks using RAGAS, DeepEval, or custom metrics aligned to business KPIs.

• Implement agent-based memory management using Mem0, LangMem or similar libraries.

• Fine-tune and evaluate LLMs for specific domains and business use cases.

• Deploy and manage AI solutions on Azure (Azure OpenAI, Azure AI Studio, Copilot Studio), AWS (Bedrock, SageMaker, Comprehend, Lex), and GCP (Vertex AI, Generative AI Studio).

• Implement observability, logging, and telemetry for AI systems to ensure traceability and performance monitoring.

• Ensure scalability, reliability, security, and cost-efficiency of production AI applications.

• Deep understanding of RAG architectures, hybrid retrieval, and context engineering patterns.

• Translate business requirements into robust technical designs, architectures, and implementation roadmaps.

• Drive innovation by evaluating new LLMs, orchestration frameworks, and cloud AI capabilities (including Copilot Studio for copilots and workflow automation).

• Programming: Expert-level Python with production-quality code, testing, and performance tuning.

• GenAI Frameworks: Strong hands-on experience with LangChain, LangGraph, LlamaIndex, agentic orchestration libraries.

• LLM Integration: Practical experience integrating OpenAI, Anthropic Claude, Azure OpenAI, AWS Bedrock, and Vertex AI models via APIs/SDKs.

• RAG & Search: Deep experience designing and operating RAG workflows (document ingestion, embeddings, retrieval optimization, query rewriting).

• Vector Databases: Production experience with at least two of OpenSearch, Pinecone, Qdrant, Weaviate, pgvector, FAISS.

• Azure: Azure OpenAI, Azure AI Studio, Copilot Studio, Azure Cognitive Search.

• AWS: Bedrock, SageMaker endpoints, AWS Nova, AWS Transform etc.

• GCP: Vertex AI (models, endpoints), Agentspace, Agent Builder.

• Master's degree in Computer Science, AI/ML, Data Science, or related field.

• Experience with multi-agent systems, Agent-to-Agent (A2A) communication, and MCP-based ecosystems.

• Familiarity with LLMOps / observability platforms such as LangSmith, Opik, Azure AI Foundry.

• Experience integrating graph databases and knowledge graphs to enhance retrieval and reasoning.