Welcome! :)
I am a research group leader in the Social Foundations of Computation department at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, hosted by Moritz Hardt.
I completed my Ph.D at the Max Planck Institute for Software Systems in Kaiserslautern, Germany, in Janurary 2026, advised by Manuel Gomez-Rodriguez. My PhD thesis was on “Predictive Accuracy and Fairness in Human-AI Teams.” During my PhD I interned at Meta, where I worked with Niek Tax, and I visited Amazon, where I worked with Dominik Janzing.
Research Interests
The ultimate goal of my research is to ensure that Machine Learning (ML) models are efficient, reliable, and safe for those interacting with or affected by them. My current (broad) research interests include uncertainty quantification in ML models (for example, using techniques such as conformal prediction and calibration), LLM safety alignment, and social and economic aspects in generative-AI.
In my free time, I enjoy playing squash, cycling, running, and calisthenics!
Recent News
- July 2026: I will be attending ICML 2026 in Seoul! Our paper Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives will be presented there as an oral presentation!
- August 2026: Our paper MCGRAD: Multicalibration at Web Scale will be presented as an oral presentation at KDD 2026 in Jeju!
- January 2026: I successfully defended my PhD!
December 2025: Our workshop on Metacognition in Generative AI will be held on December 7 at EurIPS! - December 2025: I will be presenting a poster of our NeurIPS paper on Root Cause Analysis of Outliers with Missing Structural Knowledge at EurIPS! This paper is a result of collaboration with the causality lab of Amazon AWS!
- November 2025: Our paper MCGRAD: Multicalibration at Web Scale is accepted at the KDD Applied Data Science Track! This paper is a result of collaboration with an amazing team from the Central Applied Science team at Meta.