Research-oriented ML engineer focused on structure-aware learning and reliable decision systems.
I focus on leakage-safe evaluation, probability calibration, and mechanistic probes for LLM agents in macro settings.
- Previously an ML Engineer at Bridgewater Associates (AIA Labs), building calibrated LLM forecasting systems with time-keyed evaluation and LLM-as-Judge probes.
- Previously a Quantitative Researcher at Two Sigma, developing factor-neutral cross-sectional alphas and leakage-safe walk-forward pipelines.
- M.Eng. in Computer Science and B.S. in Mathematics & Computer Science from MIT (GPA: 5.0/5.0). Worked with Alan Edelman at the Julia Lab on physics-informed neural ODEs, and Una-May O'Reilly at the ALFA Lab on neuro-symbolic cybersecurity.
- President of MIT Pokerbots, a month-long autonomous poker competition for 250+ students. This sparked my interest in game theory and reinforcement learning.
Research Interests: Probability calibration, mechanistic interpretability, scientific machine learning, leakage-safe evaluation.
Outside of work, I love working out, playing basketball, and keeping up with the latest AI/ML research.