About
Building end-to-end data systems that hold up under scrutiny.
I'm Jun — an applied data scientist based in San Diego, CA. I hold an M.S. in Applied Data Science from the University of San Diego, and bring 20+ years of experience in regulated quality systems where the cost of bad data is real and every finding needs to withstand scrutiny.
What I do
I build end-to-end data systems — from pipelines and feature engineering to deployed models and dashboards. My work sits at the intersection of analytics and engineering, with a focus on outputs that are reproducible, explainable, and defensible.
My regulated background means I approach data with a risk-based mindset. I don't just build models — I build systems designed to hold up under scrutiny.
Focus areas
- Predictive modeling and classification under class imbalance
- Data engineering — pipelines, ETL, cloud-based workflows
- NLP, sentiment analysis, and topic modeling
- Reproducible EDA and open-source Python tooling