How I work
Every project moves through four stages, from the first conversation to production.
Define
Goals, users, and constraints turn into clear requirements and measurable success criteria.
Build
Robust products with clean architecture, built across the full stack.
Refine
Tested against real usage. UX, performance, and edge cases get tightened.
Ship
Deployed to production with monitoring, documentation, and a clean handoff.
Featured Work
A selection of my most impactful projects, from AI research to production applications.
Git RAG Assistant
Local codebase Q&A with RAG: fast retrieval, grounded answers, and a simple chat UI.
Basket-AI
Affordable basketball tracking R&D: YOLO-based detections, jersey OCR, and MOT experiments.
PaperInstance-Guided UDA
Refining pseudo-labels in Unsupervised Domain Adaptation for semantic segmentation using Segment Anything Model (SAM2).
Products Shipped
Years Crafting Software
Leadership Engagements
Technologies Mastered