JJ McCauley - Full Stack Developer

AI-powered triage system for healthcare, winning 1st place at Rutgers HealthHack 2025. Currently working with Rutgers on a completer program to bring to production.

Educational 2D game that facilitates interactive morpheme exercises.

Food waste reduction platform that uses AI to predict spoilage and optimize inventory management for households.

Agent-oriented assistant that ties into a user's local obsidian vault.

Voice-first AI learning platform that turns uploaded material or any topic into a personalized roadmap with guided lessons, practice, assessments, and progress tracking.

LLM-driven platform that generates quizes and tests from user-provided material, winning 2nd best overall and best educational hack at HackUMBC 2024.

AI-based system using computer vision to accurately count chicks in poultry farms, improving standard industry efficiencies and reducing manual labor. Patent consideration.

Distributed system that optimizes SQL query execution across multiple nodes, significantly reducing processing time.

Data driven budgeting app that turns your financial data into clear insights and actionable plans.

Student analytics platform providing ML-derived insights into student performance.

Web application for managing and analyzing stock portfolios with real-time data integration and performance tracking.

Peer-to-peer chat application with end-to-end encryption for secure communication. Uses ChaCha20-Poly1305 for message encryption, Ed25519 message signatures for user validation, and UDP multicast.

Data science project collection showcasing different ETL and ML techniques on numerous different datasets.

Utilizes A* Search to automate the 15-puzzle-game, a popular game that includes shifting tiles to a sequential configuration.

Benchmarks and compares the performance of various sorting algorithms (Bubble Sort, Merge Sort, Quick Sort, etc.). One of the first projects I built.

Prototype mobile app promoting physical activity through personalized workout plans and progress tracking.

Personal portfolio website (no way who would've known!).

Develops and evaluates persona-consistent LLMs grounded in Hamlet and Macbeth via LoRA fine-tuning, RAG, and a FastAPI + React demo for single-character and multi-model dialogues.

Decision-support dashboard for a poultry farm client that analyzes litter survey data to highlight what drives performance and flag farms at risk of underperformance.