Quantitative Risk Management | Robust Portfolio Construction | Infrastructure
I am an MSc Quantitative Finance candidate at Rutgers Business School (May 2026), building upon a BSc in Finance and Economics from Kean University. I specialize in designing end-to-end Python risk pipelines that address the reality of heavy-tailed market returns. My approach bridges advanced statistical modeling—such as Extreme Value Theory (EVT) and Discrete Moment Problems (DCMP)—with scalable, production-ready code. I am actively seeking roles in the Greater NYC/NJ area where rigorous risk management and high-impact technical execution intersect.
My core philosophy is that classical Markowitz optimization is dangerously unstable with finite data. Below is my recent architecture for constructing a "Tail-Risk Parity" portfolio, demonstrating how I prioritize model-free assurances over spurious predictive alpha.
Engineered an end-to-end Python pipeline featuring a K-parallel GRU encoder (KRNN) trained via Gaussian Negative Log-Likelihood to output next-day return $(\mu)$ and volatility $(\sigma)$. Standardized residuals from this model are passed directly into downstream heavy-tail engines to isolate extreme events and prevent model misspecification.
Replaced traditional variance with a Rockafellar-Uryasev Mean-CVaR Linear Program. I modeled heavy tails using the Hill estimator (EVT) and solved a tail-anchored Discrete Moment Problem (DCMP) to generate worst-case CVaR bounds.
CVaR Objective formulation:
$$ \min \phi + \frac{1}{(1-\alpha)T} \sum_{t=1}^T z_t $$
Result: Despite the KRNN yielding $R^{2} \approx 0$, the robust CVaR constraints successfully mitigated crash risk, achieving an out-of-sample volatility of 20.5% and a highly competitive Sharpe ratio.
A robust quantitative model is useless if it cannot be deployed, and alpha is meaningless without fiscal oversight. My background extends beyond mathematics into enterprise-level budget management and Linux server architecture.
I am actively exploring full-time quantitative and risk-focused opportunities for post-graduation in May 2026. Please feel free to reach out via email or LinkedIn to discuss my research in worst-case VaR bounds, review my GitHub repositories, or talk about market infrastructure.
