A selection of things I've designed and built — from automotive diagnostics to AI-driven tooling.
A deep-learning image-classification project: custom-built and trained neural networks that recognize street-view house numbers, with a full preprocessing → training → evaluation pipeline.
A hands-free AI co-pilot for automotive diagnostics: a realtime voice agent reads a vehicle over OBD-II / CAN / UDS, narrates findings, and drives live diagnostics on screen.
A custom edge-AI ADAS platform on NVIDIA Jetson Nano — multi-camera lane detection, object tracking, and roadway mapping with real-time inference on embedded hardware.
A multi-container, full-stack ML platform that collects, forecasts, and visualizes cryptocurrency ("Runes") market data — a custom-trained LSTM served through Dockerized microservices with a real-time React dashboard.
A web app that scores a property's green-energy potential from photos: upload images, an AI vision model reviews them and scores six GAPScore categories, and a chat assistant explains the results and next steps.
Agentic AI wired into real workflows — OpenAI Agents SDK tool-calling, LangChain / LangGraph orchestration, and RAG memory over live data streams.