Hire Ajinkya B. - RAG Engineer

* As an AI Engineer, I’m currently focused on building Agentic AI systems that integrate Large Language Models (LLMs) with advanced orchestration frameworks like Model Context Protocol (MCP), Agent-to-Agent (A2A), and LangGraph. * Key responsibilities include: * Designing and deploying intelligent multi-step agents capable of tool use, memory, and decision-making. * Building Retrieval-Augmented Generation (RAG) pipelines and integrating LLMs with structured tool APIs to enable contextual and autonomous behavior. * Working with cutting-edge GenAI frameworks including LangChain, DSPy, and Open Source LLMs (LLaMA, Qwen, Mistral) via OpenAI, Ollama, and Groq backends. * Optimizing inference, retrieval, and decision latency using Vector DBs (Milvus, FAISS) and FastAPI microservices. * Implementing MLOps / LLMOps best practices, version control, and continuous deployment pipelines for scalable AI agent infrastructure.