Hi, I'm
Beege!
Or Bryan Berry if you want to be boring and legal
Engineering leader, builder, and community organizer based in Seoul.
Projects
An AI-powered radiology training platform that helps medical students and radiologists sharpen their diagnostic skills. Students write diagnostic reports for chest X-rays, and the system compares them against expert ground truth using multi-step LLM analysis — delivering finding-by-finding scoring, educational feedback, and actionable improvement suggestions in real time via streaming.
Built for the Spoon OS hackathon with CodeSeoul. Uses a graph-based LLM workflow (SpoonAI SDK) to orchestrate comparison, with FAISS-powered semantic search for RAG-based image retrieval and a multi-dimensional scoring system covering similarity, completeness, accuracy, and medical terminology.
VizPlan
A SaaS tool for engineering leaders to visualize alignment between company goals and the work teams are actually doing. Connects to project management tools (Jira, Linear, etc.) and surfaces where planned work drifts from strategic objectives — giving leaders real visibility without micromanaging.
Built as part of Hapsen, the company I co-founded. Designed with a bidirectional sync strategy to meet teams where they already work. Currently in the problem validation and early prototype stage.
Model Server
A self-hosted LLM inference server for running open-weight models locally. Built to support a medical device AI application — providing diagnostic assistance for field/service maintenance of imaging devices (starting with ultrasound).
Designed to run models like Qwen on local infrastructure, avoiding vendor lock-in and VPN dependencies. Part of a co-venture focused on bringing AI-assisted diagnostics to all imaging device types.
About
Placeholder — your story goes here.
Experience
Role Title
Company — 2024–Present
Description placeholder.
Community
Placeholder — CodeSeoul, mentoring, events.