I build models that survive walk-forward testing — then ship them as real APIs and dashboards. Not notebooks. Production.
- 🔀 3 merged PRs to
yfinance— a 22k★ production library, actual maintainer-reviewed code - 📊 Alpha Engine — multi-factor model on Nifty 50, Sharpe 5.87, walk-forward validated with Deflated Sharpe Ratio
- 🎲 Derivatives Pricing Engine — Black-Scholes, Binomial CRR, Monte Carlo (100K paths); put-call parity verified to 0.000000
- 🧠 FinBERT Sentiment Pipeline — 0.96 Macro F1, 4-stage NLP pipeline, stress-tested on live headlines
- 🏦 Credit Risk API — gradient boosting (0.77 AUC), calibrated probabilities, serverless FastAPI on Vercel, React dashboard
- 🔗 Live, working endpoint — hit it right now, it's real
- 🐳 Model training → REST API → Postgres → React UI → containerized deploy
Open to quant/ML engineering roles — remote, globally.