π Delaware, USA | π Astroparticle Physicist | π€ GNN & ML Researcher
Bridging the gap between High-Energy Physics and AI. Currently decoding the universe at the IceCube Neutrino Observatory while building local-first AI tools and regional platforms.
- β¨ AutoML-Research β Autonomous ML experimentation for any project. Inspired by Karpathy's autoresearch β the same constraint-driven experiment loop, adapted to work with any ML project, any framework, any AI agent.
- π°οΈ Multiple ML Works @ IceCube Observatory (Public Soon) β Architecting multiple Graph Neural Networks, CNN and other ML method pipelines and models for reconstruction of Extensive Air Showers (EAS) in Antarctica.
- π€© NotesGutter (600+ downloads π₯³) - Anchors rich markdown notes and infinite-canvas drawings to your code, without making your code messy
- π TalkToCode (Public Soon) β Local-first AI coding assistant. Chat with your codebase privately using RAG and open-source LLMs.
- π» GitOn - A feature-rich, deeply integrated Git extension designed to supercharge your version control workflow
- π₯ Shello & ShelloHub - Turns any Linux server into a secure, browser-accessible terminal, bypassing the need for VPNs, port forwarding, or root privileges. Also a combined dashboard to manage multiple Shello instances
- π ShelfScan (Public Soon) - Scan any shelf to automatically read book titles, categorize, give ratings etc and locate any specific item on the shelf. This is built out of pain of finding good books at GoodWill.
- Φ GPT Search - Prompt ChatGPT directly from your browser's address bar
- πΌ Job Tracker - Track job applications with one click. Never lose track of where you applied.
- π Git Notes - Context-aware notes for your GitHub repositories.
- π· Training Script Runner - Stop "fat-fingering" terminal arguments
- Geometric Deep Learning β Focused on the application of GNNs to radio astronomy and particle reconstruction.
- Quantitative Finance β Exploring the intersection of ML and high-frequency trading.
- AI SaaS Architecture β Rapidly prototyping AI-native products with a focus on local inference.
"If it can be modeled as a graph, it should be."