Multiple Fully-Funded PhD Positions in Responsible AI at University of Vienna
The newly established Responsible Machine Learning (ML) Group at the Faculty of Computer Science, University of Vienna, is looking for multiple outstanding candidates (fully-funded PhDs) to join the team. Led by Prof. Dr. Martin Pawelczyk, our research sits at the intersection of AI Safety and Data-Centric AI. The overarching aim of our group is to make large-scale machine learning more reliable, transparent, and aligned with human values. Joining our team as an early member will allow you to shape our research culture and tackle high-impact projects from the ground up in a world-class research environment.
We are specifically looking for highly motivated talent with a strong quantitative background and interest in (at least) one of the following areas:
- Data-Centric AI (machine unlearning, data attribution, and privacy preservation for large foundation models)
- AI Safety (robust alignment in multi-agent LLM systems)
- Mechanistic Interpretability (understanding the fundamental drivers of large models)
