🎓 CS @ Georgia Tech (Dec 2025) · 🎓 Incoming Baruch MFE (Fall 2026)
📊 Aspiring Quant Researcher / Trader / Developer
💼 Experience: Morgan Stanley (SWE Intern → Incoming Equity Derivatives Strats Intern) · Equifax (ML Engineer Intern) · Georgia Tech Student Foundation (Senior Quant Director)

• ⚡ Build execution algorithms, trading signals, and backtesting frameworks
• 📈 Research time-series models, volatility surfaces, and deep learning in markets
• 🏦 Manage and mentor a 37-analyst team running a $50K systematic quant portfolio inside a $2.6M endowment
• 🧮 Work at the intersection of derivatives, stochastic modeling, and ML with a focus on alpha generation & risk

• Languages: Python · C++ · SQL · Java · TypeScript
• Libraries/Tools: NumPy · Pandas · scikit-learn · statsmodels · PyTorch · TensorFlow · Backtrader · Plotly/Dash · Streamlit
• Quant: Factor modeling · Time-series (ARIMA/GARCH, SARIMA) · Monte Carlo simulation · Vol surfaces & SVI · Risk-neutral densities · Portfolio optimization · IBKR API
• Infra: Kafka · Docker · Git · Linux · Azure DevOps

• 📊 Option-Density-Viz
  Extracted risk-neutral densities from BTC/ETH options (Deribit API), fit arbitrage-free SVI smiles, applied Breeden–Litzenberger and COS methods, and built Plotly dashboards for vol surfaces, densities, and higher moments.

• 🤖 Financial Markets RL Simulator
  Multi-agent RL limit order book simulator (SPY, BTC, 10Y) with realistic frictions. PPO/SAC agents achieved ~39% CAGR and Sharpe ~1.3 over a 10-year backtest, with rich diagnostics (drawdown, PnL decomposition, entropy-regularized rewards).

• 📐 Neural PDE Models for Option Greeks
  Physics-informed neural network embedding the Black–Scholes PDE to generate option Greeks across strikes, maturities, and volatilities, delivering faster and smoother sensitivities than finite-difference and vanilla Monte Carlo.

• 🏦 Company Bankruptcy Predictor
  End-to-end ML pipeline to forecast corporate bankruptcy from financial ratios. Trained Logistic Regression, Random Forest, SVM, Gradient Boosting, and Neural Nets; best SVM (RBF) model reached ~96–97% accuracy with strong recall on distressed firms.

• 📫 Email: drew.verzino@gmail.com
• 💼 LinkedIn: linkedin.com/in/drew-verzino