Data science student at SJSU turning raw data into deployed ML applications, from custom datasets to production RAG pipelines.
A conversational AI assistant that answers natural language NBA questions grounded in real-time stats. Built with a RAG pipeline combining structured stat lookups with semantic vector search over 478 player and team summaries. Ask it anything about the current season and get answers backed by actual numbers.
Full-stack ML application predicting NBA MVP, DPOY, and Sixth Man awards using a custom dataset of 16,500+ game-level records scraped from Basketball Reference. Applied K-Means clustering to classify 340+ players into performance tiers, with an interactive dashboard featuring award leaderboards, radar charts, and real-time prediction tools.
Python, SQL, Java, C, C++
LLMs, NLP, RAG Pipelines, Vector Embeddings, LangChain, ChromaDB, Scikit-learn, TensorFlow, XGBoost, Claude API, OpenAI API, Hugging Face
Pandas, NumPy, Plotly, Matplotlib, Seaborn, PostgreSQL, BigQuery, dbt
Git, Docker, FastAPI, Streamlit, ChromaDB, AWS, GCP, REST APIs
Built end-to-end data pipelines in Python and SQL, developed automated analytical dashboards for IT service performance, and architected optimized SQL workflows that accelerated report generation across cross-functional teams.
Diagnose and resolve hardware, software, and network issues for 20+ customers weekly. Implement security measures and optimize device configurations across Windows, macOS, and mobile platforms.