Data Science undergraduate building RAG systems, NLP pipelines, and scalable data applications.
I am a Data Science undergraduate specializing in NLP, Retrieval Augmented Generation (RAG) systems, and data pipelines. I design and build RAG-based systems with a focus on retrieval quality, evaluation, and real-world deployment performance.
RAG system for real-time event queries, serving 400+ attendees. Optimized latency from 4.2s to 18ms (for cached responses) via multi-tier caching and cross-encoder reranking. Managed a development team as Technical Lead.
Built a self hosted cloud storage system with an integrated RAG pipeline for querying technical PDFs. Implemented a retrieval strategy using hybrid search, re ranking, and context sufficiency checks to prevent hallucinations. Features asynchronous document ingestion and citation tracking, optimizing the system for faithfulness and measurable retrieval accuracy.
Full-stack web app for real-time news sentiment analysis. Scrapes articles, calculates VADER polarity scores, and classifies topics using a custom NLP pipeline.
Contributor to Keras — merged pull request in core ML ecosystem
