Rising junior at Virginia Tech double majoring in Data Science and Statistics (minors in Mathematics & Economics). I build quantitative finance tools and ML pipelines, and I've worked with production-scale data systems in internships. I'd rather report a 54% accuracy that's real than an 87% that isn't.
Contributing to open source, continuously retraining and stress-testing my models, and keeping my codebases sharp as new data comes in.
Quantitative finance tools, financial ML pipelines, or anything at the intersection of statistics and systems — backtesting frameworks, portfolio optimization, signal research, or production deployments of data-heavy models.
Deep learning fundamentals and PyTorch, my current stack is classical ML (LightGBM, Scikit-Learn, cvxpy) and I'm actively closing that gap. Also interested in learning from anyone who has built production quant systems beyond the academic/personal-project scale.
PyTorch and deep learning foundations. Also deepening my understanding of stochastic calculus and risk-neutral pricing beyond what I've implemented in my option pricer. On the tooling side, I'm learning how to incorporate AI into my workflows and exploring AI engineering more broadly.
Walk-forward validation done right: per-fold scaler and PCA fitting, not global. And control variate Monte Carlo: using a geometric Asian closed-form to make arithmetic Asian pricing dramatically more efficient.
My original passion was marine biology. Then I discovered that following your passion doesn't always pay the bills, so I pivoted to pricing derivatives and building ML pipelines instead. Turns out I'm equally fascinated by both; one just has better exit opportunities.
