Founded AI Safety Saarland, a student-led organization facilitating interdisciplinary exchange, education, and research around AI safety and governance.
Research Experience
Researching at the Interdisciplinary Institute for Societal Computing on context-dependent user risk evaluations for LLMs.
Education
Fifth-semester bachelor’s student studying Data Science and AI at Saarland University, Germany, under the supervision of Goran Radanović and Adish Singla, working on her thesis at the Max Planck Institute for Software Systems.
Background
Passionate about AI safety, both in the technical and governance aspect, believing it is one of the most pressing issues at this time. Focusing on redteaming for misalignment in AI agents for her thesis.
Miscellany
Shares her journey into the field through her blog, aiming to break down complex concepts and problems into understandable terms for everyone.