Analysis, engineering,
storytelling.
ML engineer and data scientist. Data analysis, visualization, prompt engineering, and communication.
Technical toolkit.
Python
- Pandas
- NumPy
- Matplotlib
- Seaborn
- Scikit-learn
- PyTorch
Data
- SQL
- Power BI
- Excel
- ETL Pipelines
Tools
- Git / GitHub
- Jupyter
- Docker
- AWS
Other
- Adobe Illustrator
- Adobe Premiere
- Photoshop
Where I've worked.
Data Scientist / ML Engineer
Sentien AI
- Built a synthetic data generator for a phone fraud detection product.
- Engineered the company's core data infrastructure from the ground up.
- Implemented ML pipeline that identifies and predicts scam behavior.
Data Scientist
PayTomorrow
- Built the company's ETL pipelines from scratch.
- Implemented a layered ML model in the underwriting flow that significantly boosted customer acceptance and discernment.
- Greatly decreased rates of fraud through improved model precision.
IB DP English Literature / Theory of Knowledge Teacher, Basketball Coach
International Schools + K-12
- Taught IB DP English Literature, Language and Literature, and Theory of Knowledge across international school settings in China and Germany, alongside earlier ESL and K-12 classroom work.
- Designed curricula, led discussion-driven classes, and supported students from a wide range of cultural and academic backgrounds.
- Coached basketball across varsity, JV, middle school, camps, and private training, using the game to build discipline, resilience, and team culture.
Selected projects.
Used Car Price Prediction
Gradient-boosted regression model for used-car valuation on large, messy marketplace data. Compared LightGBM and CatBoost, handled mixed categorical features, and balanced model quality against inference speed.
Airport Taxi Demand Forecasting
Hourly time-series forecast for airport taxi demand using lag features, seasonality analysis, and temporal validation. Compares a seasonal baseline, random forest, and XGBoost against a stated RMSE target.
Gold Recovery Process Modeling
Multi-stage regression pipeline to predict rougher and final gold recovery from plant telemetry. Cleans process data, validates recovery calculations, tunes models with mean squared error, and evaluates a weighted sMAPE business metric.