Chandan Yadav

I've built backend systems and AI-powered applications focused on scalable data processing, reliable APIs, and real-time workflows. At Entorhino AI, I architected a document research chatbot using RAG and semantic search across more than 10,000 indexed document chunks.

I designed its modular ingestion, embedding, retrieval, and generation layers, then implemented OCR and vector indexing pipelines that reduced query latency by 30%. I also containerized services with Docker and integrated CI/CD for automated deployment.

My projects include a distributed URL shortener built with FastAPI, PostgreSQL, Redis, and SQLAlchemy, with caching, transactional consistency, analytics, and optimized lookups. I also built an automated ML pipeline that trains and evaluates models on 10K+ record datasets, identifies diagnostic issues in under two seconds, and uses LLM-based reasoning for root-cause analysis.

I have completed my B.Tech in Computer Science & Engineering with AI & ML, and I enjoy designing modular systems that are efficient, maintainable, and ready to scale.