I am a Postdoctoral Scientist at Amazon Web Services (AWS) working on Responsible AI (RAI).
My current research explores the use of Large Language Models (LLMs) to synthesize and augment data for RAI evaluation, as well as understanding how humans build trust in LLM systems.
More broadly, my work sits at the intersection of machine learning and socially consequential domains, with an emphasis on algorithmic fairness.
During my PhD, I adopted a data- and problem-centered approach to study the impact of noise, proxies, and dynamics on fairness in machine learning.
Before joining AWS, I received a PhD in Statistics and Machine Learning (2023) from Carnegie Mellon University where I was advised by Alexandra Chouldechova and Zachary Lipton.
Prior to that, I graduated with a Master of Science in Mathematics from the University of Freiburg in Germany in 2018. Before that, I obtained a Bachelor of Science in Economics (2017) and a Bachelor of Science in Mathematics (2015) from the University of Freiburg.
Last updated: December 2024