I frame problems with data and deliver answers through pipelines.
- 🔬 Data Scientist / Data Specialist based in Seoul, Korea
- 🧊 Open-source contributor to Apache Iceberg (PyIceberg) & Apache Airflow
- 📄 I enjoy structuring unstructured data — e.g., an OCR + LLM post-processing pipeline for insurance claim documents
- 📊 From statistical modeling to data engineering, I care about making analyses reproducible and production-ready
Languages
Data Science & ML
Data Engineering
| Project | Description | Stack |
|---|---|---|
| 🧾 insurance-ocr-llm-project | OCR extraction of insurance claim forms with LLM-based post-processing | Python OCR LLM |
| 🏙 population-outflow | Analysis of regional youth population outflow and tailored job-attraction strategies | Jupyter Statistics |
| 🧊 apache/iceberg-python | PyIceberg — open-source contributions | Python Lakehouse |
| 🌬 apache/airflow | Apache Airflow — open-source contributions | Python Orchestration |
