At CITIC CLSA Pune, I engineered a RAG embedding pipeline and Qdrant vector knowledge base to chunk and index 263 operational documents. I used Docling to convert complex PDFs and DOCX files into structured Markdown, and collaborated on integrating the pipeline with an LLM retrieval system for an operational chatbot.
In my projects, I scraped and structured Indo-Pak ceasefire incident data for analysis, and developed an online payment fraud detection platform with a React frontend and FastAPI backend. I’m pursuing an MSc. in Data Science and Big Data Analytics at MIT-WPU.
