I am leveraging statistical modeling techniques, convex optimization, and machine learning to develop AI prototypes that address problems across the firm. My current projects range from forecasting operational risk to suggesting salary ranges in a systematic way to comply with regulatory requirements.

I employed statistical modeling and convex optimization to engineer a comprehensive portfolio optimization strategy, enhancing tax efficiency by incorporating future tax implications via a custom tax alpha term. In addition, I designed a comprehensive backtesting suite using Python, CVXPY, and Pandas to assess the strategy's performance on synthetic asset data. I also worked on a project that aimed to reduce risk in factor portfolios; in backtesting, my methodology improved Sharpe ratio without sacrificing returns. I worked under Stephen Boyd, Emmanuel Candès, Trevor Hastie, and Mykel Kochenderfer.

Teaching Assistant, EE364a: Convex Optimization, Stanford University (Winter 2023)- Assisted Prof. Stephen Boyd in instructing a graduate course with 234 students, focusing on convex optimization techniques and applications- Conducted 4 hours of weekly office hours to provide personalized support and clarify course concepts for students- Collaborated in designing and grading final exam- Actively contributed to course forum (Ed) by addressing student inquiries

Completed a group research project for Stanford Undergraduate Research Institute in Mathematics (SURIM) 2021 about Tokuyama's formula, which provides a combinatorial evaluation of an important function in representation theory.