Deepak Yadav

I’m a Generative AI Engineer with ~3 years of hands-on experience designing, deploying, and scaling AI-driven applications. I specialize in the full GenAI stack—LLMs, RAG pipelines, and AI agents—backed by strong prompt engineering and Python development.

In my recent work, I designed and deployed a generative AI application for natural language querying of SQL databases, delivering production-ready structured reports through Python, FastAPI, and OpenAI. I architected scalable agent workflows for query routing, NL-to-SQL conversion, and JSON output generation, integrating into existing enterprise data systems via REST APIs.

Previously at HCLTech, I built and deployed AI agent and copilot solutions with LangGraph and Azure OpenAI to automate enterprise support workflows. I also developed RAG pipelines using vector embeddings and semantic search with LlamaIndex, and I implemented model evaluation frameworks to reduce hallucinations while optimizing for latency and cost.

I care deeply about output reliability and responsible AI practices, so I build with evaluation, monitoring, and governance in mind. My projects span vectorless RAG, multi-agent supervisor orchestration, and production RAG web applications deployed on Azure, plus applied ML for phishing URL detection and email spam classification.