I’m a Computer Science student at Purdue University with a concentration in Machine Learning. I enjoy learning the problems different industries face and buliding data-driven solutions to try my best in solving them.
This is my little corner of the internet - projects, experiments, certificates, and whatever I’m learning along the way.
/about_me
I’m currently a ML Data Engineer at Team ACP Racing where I'm building a Python ETL pipeline to capture live data to conduct race strategy adjustments.
I'm currently in my junior year pursuing my bachelors in Computer Science at Purdue University.
Here are some technologies I work with often:
- Python
- Pandas / NumPy
- scikit-learn
- PyTorch
- SQL
- R
Outside of work, you’ll usually find me hiking, playing anything that involves a racket or paddle, and catching Steelers games. Oh! I'm also an avid mixologist.
/experiences
Machine Learning Data Engineer
Team ACP Racing | World Racing League
September 2025 - Present · Indianapolis, IN
Engineered Python ETL pipeline (REST APIs, WebSocket/SignalR) to capture live motorsports telemetry in 3 second intervals
Designed an automated 15+ feature extraction system deriving performance metrics, enabling time series analysis for race strategy
Implemented OAuth 2.0 authentication with automated token lifecycle management, securing API access for 6+ hour events
/projects
Ames Housing Price Analysis
Statistical and ML analysis of how basement, first-floor, and second-floor square footage differently impact home prices.
selected
Radar Signal Processing Simulator
Radar simulation demonstrating signal processing pipelines, target detection algorithms, and multi-target tracking with Kalman filtering.
click
Java Chat Application
Real-time client-server messaging system with Swing GUI and optional MySQL persistence.
click
Ames Housing Price Analysis
Statistical and ML analysis of how basement, first-floor, and second-floor square footage differently impact home prices.
Diagnosed multicollinearity (VIF > 100) and heteroscedasticity (Breusch-Pagan test); applied log transformation and bootstrap inference (2,000 reps) for robust standard errors.
Validated with 10-fold cross-validation and Extra Sum of Squares F-tests; confirmed model generalization with identical training/CV RMSE.
Extended with Ridge, Lasso, and Elastic Net regularization; expanded to 10 predictors and improved R² from 0.62 to 0.79.
/film_strip
Purdue x Google AI Summit