Work
Research projects, experiments, and open-source tools.
A macOS app that suggests meals from ingredients already in your pantry. A LangGraph agent searches a PostgreSQL collection of 501 recipes and lists the ingredients you still need for each suggestion.
A computer-vision project exploring neural architecture search for compact convolutional networks. It focuses on finding a practical balance between model size and predictive performance, so a selected network can be efficient as well as capable. The repository demonstrates a search-based approach to designing lightweight CNN architectures for image-classification tasks.
A reinforcement-learning simulation for traffic lights that learns signal actions from changing road conditions. Using a Deep Q-Network, the controller adapts its choices as traffic shifts, with the goal of reducing waiting and congestion. The project offers a compact testbed for exploring how learned traffic control behaves across different simulated scenarios.
An experimental retrieval-augmented generation pipeline that searches for relevant passages before producing an answer. It is designed to keep responses tied to supporting evidence, making it easier to inspect where an answer came from and reduce unsupported claims. The project explores similarity-based retrieval and evidence-aware response generation for research and question-answering workflows.