Their fresh perspectives and exceptional research expertise are set to significantly advance the Institute’s mission and open exciting new opportunities for collaboration in the future.
Dr. Maksym Andriushchenko and Dr. Maximilian Dax will join in September, followed by Dr. Sahar Abdelnabi in October. All three will be co-affiliated with the Max Planck Institute for Intelligent Systems (MPI-IS) and the Tübingen AI Center as Independent Research Group Leaders.
Find out below about their research focus and short bio.
Dr. Maksym Andriushchenko
Research Group: AI Safety and Alignment
Start Date: September 1, 2025
The new AI Safety and Alignment Group focuses on developing technical solutions to reduce risks from general-purpose AI models. We are particularly interested in alignment of autonomous LLM agents, which are becoming increasingly capable and pose a variety of emerging risks. We are also interested in rigorous AI evaluations and informing the public about the risks and capabilities of frontier AI models. Finally, we aim to advance our understanding of how AI models generalize from training data, which is crucial for ensuring their steerability and alignment with societal values.
Maksym Andriushchenko is a postdoctoral researcher at EPFL and an ELLIS Member. He has worked on AI safety with leading organizations in the field (OpenAI, Anthropic, UK AI Safety Institute, Center for AI Safety, Gray Swan AI). He obtained a PhD in machine learning from EPFL in 2024 advised by Prof. Nicolas Flammarion. His PhD thesis was awarded with the Patrick Denantes Memorial Prize for the best thesis in the CS department of EPFL and was supported by the Google and Open Phil AI PhD Fellowships. He did his MSc at Saarland University and the University of Tübingen, and interned at Adobe Research.
Dr. Maximilian Dax
Research Group: Science and Probabilistic Intelligence (SPIN)
Start Date: September 1, 2025
The group for Science and Probabilistic Intelligence (SPIN) combines foundational research on probabilistic AI with applied research in science. We work on a range of scientific domains, aiming to drive discovery through machine learning. Outside of such applications, our AI research focuses on generative modeling, inverse problems and simulation-based inference, aiming to develop efficient, accurate and reliable methods.
Maximilian Dax is a postdoctoral researcher at ETH Zurich and the ELLIS Institute Tübingen and a member of the LIGO Scientific Collaboration. He completed his PhD at the Max Planck Institute for Intelligent Systems in Tübingen under supervision of Bernhard Schölkopf and interned at Google Research. His research focuses on probabilistic inference, generative modeling and density estimation, with an emphasis on scientific applications. Together with his collaborators, he developed DINGO, a leading machine learning approach for gravitational-wave data analysis.
Dr. Sahar Abdelnabi
Research Group: COMPASS
Start Date: October 1, 2025
The new research group, COMPASS (COoperative Machine intelligence for People-Aligned Safe Systems), will focus on developing safe, aligned, interpretable and steerable AI agents with emphasis on security, human aspects, and cooperative multi-agent systems.
Sahar Abdelnabi is an AI Security Researcher at Microsoft Research Cambridge, UK. Her research interests span the broad intersection of AI with security, safety, and sociopolitical aspects. She received her master’s degree from Saarland University and completed her PhD summa cum laude at the CISPA Helmholtz Center for Information Security. One of her papers was the first to identify the indirect prompt injection problem in LLM-Integrated applications, a fundamental vulnerability in all existing LLMs.
- Find out more about the current research groups at the ELLIS Institute Tübingen here.