PhD Positions in Responsible AI
- Hiring Organisation
- Universität Wien
- Location
- Innere Stadt, Wien, Austria
- Employment Type
- Permanent
- Salary
- EUR Annual
Science. Led by Prof. Dr. Martin Pawelczyk, who recently joined the University of Vienna from Harvard University, our research sits at the intersection of AI Safety and Data-Centric AI. We aim to make large-scale ML more reliable, transparent, and aligned with human values. We are specifically interested … Data-centric AI: Advancing machine unlearning, privacy-preserving techniques, and robust data curation. AI Safety: Ensuring robust alignment and safety in multi-agent LLM systems Efficiency: Streamlining large-scale model experimentation and training. Science of Deep Learning: Exploring mechanistic interpretability and understanding the fundamental drivers of model performance at scale. ...