I am a Member of Technical Staff at OpenAI, working on safety research.
Previously at Amazon, I developed LLM evaluation and alignment systems at scale, including work on safety assessments, red teaming, fairness evaluation, and structured reasoning for reducing over-refusals. I also developed a unified tabular deep learning framework for internal prediction tasks, a weakly-supervised topic modeling system for large-scale document analysis, and agent-based systems for internal applications. My work has resulted in publications in venues including ACL, EMNLP, COLM, TMLR, and KDD.
Prior to Amazon, I served as a Senior Data Scientist at Schlumberger, where I co-founded the company's first data science team dedicated to addressing employee attrition challenges through transformer-based deep learning techniques.
I hold a Master of Arts in Statistics from the University of California, Berkeley (2018), and a Bachelor of Science in Applied Mathematics with a minor in Computer Science from the University of Toronto (2017).
