Hi! I'm currently a second year master's student at MIT studying EECS and entrepreneurship. Before MIT, I worked as a software engineer at Amazon on truck/train routing algorithms and large scale optimization problems for their fleet across North America and Europe. I completed my undergrad at Georgetown University where I double majored in computer science and economics.
In the past year, I've been trying to transition into working as an AI safety researcher. My research interests are on societal impacts of AI, behavioral evaluations (particularly sycophancy), and human-AI interaction. I'm currently working on publishing the research I did through SPAR on sycophancy in large language models and how it manifests with different, complex personas. I'm also working on publishing the research I'm doing through SERC at MIT on training risk-averse AI (I focus on reward model training).
Research
Writing
Experience
Risk-Averse AI & Training AI Utility Functions
Sycophancy & Model Organisms of Conditional Misalignment
Agentic Reinforcement Learning for Competitor-Aware Customer Retention
Electrical Engineering & Computer Science (EECS), Leaders for Global Operations (LGO)
Transportation Optimization (MMPO)
Previously called Business Development
Leveraging Prior Concept Learning Improves Generalization From Few Examples in Computational Models of Human Object Recognition
Computer Science & Economics