B.S. student in Computer Convergence Software at Korea University, Sejong Campus, graduating in February 2027. I'm preparing for software engineering and applied AI roles in the United States.
My projects span machine learning pipelines, AI agent workflows, and practical web applications. I enjoy turning a problem into a working tool, then making its behavior and limitations easy to understand.
Contact: honeybeelawn@gmail.com · LinkedIn
| Project | What to explore | Technologies |
|---|---|---|
| Engine RUL Prediction | Parallel HDF5 processing and CNN experiments on NASA N-CMAPSS simulated engine data, with recorded results and evaluation caveats. | Python, PyTorch, HDF5 |
| ETF Answer Agent · Live demo | A prototype question-answering workflow with retrieval, validation gates, and revision routing. | Python, LangGraph |
| Multi-Agent BEMS | Capstone project (Excellence Award): a LangGraph supervisor routes operator questions to monitoring, analysis and report agents over simulated building-energy data, with rule-based alerts and fallbacks. | Python, LangGraph, FastAPI, Next.js |
| BEMS Anomaly Operations Center | Building-energy sensor data recovery, rule-based diagnostics, and an operations dashboard. | Python, FastAPI, Streamlit |
- MOA — AI-powered civic reporting: Contributed AI classification, the React admin console, and report grouping and prioritization in a university industry-practice team project. See the merged classifier and admin console pull requests. The linked deployment currently demonstrates the frontend; the backend runs locally.
- BidderBidder iOS: Contributed login/signup flows, Firebase phone verification, search UI, and SwiftLint CI through merged pull requests for a used-goods auction app.
Python · JavaScript · Swift · SQL
PyTorch · scikit-learn · LangGraph · FastAPI · Streamlit · React · Next.js · Git
For implementation details, setup instructions, and experiment evidence, start with the linked project READMEs.