cv

Quantitative Researcher, Systematic Volatility

Squarepoint Capital

At Squarepoint Capital, I work as a Quantitative Researcher on the Systematic Volatility team, developing short-horizon risk forecasts and alpha signals for SPXW 0DTE options. My research focuses on predicting open-to-close realized volatility by extracting and modeling intraday features such as futures order flow, auction pressure, and order book imbalance. I build execution-aware signal pipelines and scalable multi-asset backtests that account for signal decay, transaction costs, and cross-sectional performance. To support live trading, I automate theoretical IV and delta computations, manage real-time data ingestion, and maintain model inference pipelines in Python and C++, with performance-critical components implemented in multi-threaded C++ using custom data structures. My work is closely integrated with portfolio managers and execution teams to ensure research outputs translate directly into capital allocation, position sizing, and execution logic under systematic risk constraints.

• Short-Horizon Realized Volatility Forecasting
• Intraday Feature Engineering from Futures and Order Book Data
• Execution Slippage and Market Impact Modeling
• Volatility Arbitrage Signal Construction
• Scalable Cross-Sectional Backtesting Frameworks
• Implied Volatility Surface Construction and Stress Testing
• Low-Latency, Multi-Threaded Trading System Development in C++
• Real-Time Data Ingestion and Pipeline Orchestration
• Auction Dynamics and Market Microstructure Analysis
• Capital Deployment Optimization under Risk Constraints

Quantitative Engineer

Rothschild & Co., RMM Actions USA

I focused on developing statistical arbitrage strategies using advanced time series modeling techniques and machine learning algorithms. I built and optimized machine learning models for forecasting asset price movements and identifying arbitrage opportunities. I collaborated with traders to design and implement trading strategies, leveraging Markowitz portfolio optimization theory. Additionally, I applied LSTM and GARCH models to analyze financial time series data, enhancing the accuracy of predictions and minimizing risk exposure.

• Statistical Arbitrage
• Machine Learning
• Time Series Modeling
• LSTM
• GARCH
• Markowitz Optimization

Quantitative Research Intern, Volatility Modeling Systems

MIT CSAIL, Laboratory for Financial Engineering

At MIT CSAIL’s Laboratory for Financial Engineering, I conducted research on volatility modeling systems, developing arbitrage-free implied volatility surfaces using SVI and constrained spline methods under illiquid and noisy market regimes. I evaluated robustness of volatility surface inference under stress environments, integrating deep learning models—such as LSTM, GRU, and convolutional architectures in PyTorch—to improve conditional surface estimation. I also designed backtesting frameworks for stochastic volatility models and engineered infrastructure for scalable inference pipelines in Python and C++, contributing to model deployment and diagnostic tooling across research workflows.

• Volatility Surfaces
• SVI Calibration
• Deep Learning
• Neural SDEs
• Stochastic Models
• Time Series
• PyTorch
• C++
• Backtesting
• Diagnostics

Data Scientist, Financial Risk Advisory

Deloitte Canada

I developed and deployed machine learning models to assess and predict financial risks, focusing on market and credit risk. I built data pipelines for collecting, aggregating, and preprocessing financial data, and implemented models like random forests and gradient boosting to forecast risk events. I validated the models by comparing predictions with historical data to ensure accuracy and compliance with industry standards. I also automated the generation of risk reports and collaborated with financial analysts to extract actionable insights for optimizing risk management strategies.

• Python
• R
• Power BI
• Random Forests
• Gradient Boosting

Bachelor's of Computer Science

University of Waterloo, David R. Cheriton School of Computer Science

Computer Science, Data Science Specialization

• Machine Learning
• Data Structures
• Object-Oriented Software Development
• Neural Networks
• Numerical Computation
• Mathematical Statistics
• Stochastic Process
• Operating Systems

Star-Friedman Scholars - Harvard University

Harvard T.H. Chan School of Public Health

Awarded the Star-Friedman Challenge for Promising Scientific Research alongside Professor Tanujit Dey and Professor Francesca Dominici for promising research in statistical time series modelling and public health research.

A Review on the Biological, Epidemiological, and Statistical Relevance of COVID-19 paired with Air Pollution

Environmental Advances

This narrative review critically evaluates recent studies on the associations between various air pollutants—CO, NO2, O3, PM2.5, PM10, and SO2—and COVID-19 outcomes, examining their individual and combined effects across different regions and exposure periods, while also exploring the biological mechanisms underlying these associations.

Lag time between state-level policy interventions and change points in COVID-19 outcomes in the United States

Patterns: Cell Press, Harvard University

The research focused on using a data-driven search algorithm to detect change points in COVID-19 case and death trajectories, correlating these changes with state-level policy implementations.

Association of temporary Environmental Protection Agency regulation suspension with industrial economic viability and local air quality in California, United States

Environmental Sciences Europe

The study used machine learning models to predict weekly employment data and t-tests to assess the economic impact of the EPA's 2020 enforcement regulation rollbacks on oil and manufacturing industries, as well as on air quality in California, ultimately finding no economic growth and continued pollution despite the suspensions.