Built serverless dashboard using React & Supabase with PostgreSQL database, Edge Functions, and Row Level Security. Integrated Stripe API for subscription management and proprietary voice engine webhooks for real-time call analytics, processing 100+ daily call events with automated data synchronization via Edge Functions. Developed admin panel with business account management, call history filtering for serving Triangle area businesses.

Classifies breast histopathology images as benign or malignant, comparing web-scraped vs. professional medical datasets. Trained ResNet34 on 555,000+ medical images from 279 patients, achieving 88.6% accuracy. Built baseline ResNet18 model using 143 web-scraped images achieving 82% accuracy.

Led frontend development team for a mobile application that helps students forecast their GPA and receive personalized academic advice by uploading transcripts to Google's Gemini API. Developed GPA Forecaster screen with dynamic course modification and transcript upload functionality. Integrated backend+frontend for modifying courses, terms, and transcript data with SQLite.

Flask-based decision-making web application that features weighted pros-and-cons for decisions, featuring user authentication, decision archiving, real-time visualization of decision scale, and a recommendation system. Featured in Harvard's prestigious CS50 Gallery of Final Projects for innovative use of Python, Flask, and SQL.