Project cooperationUpdated on 16 January 2026
Postdoc in AI interpretability, safety, control
About
Our group has multiple available projects in AI, including AI safety, unlearning from LLMs, interpretability, controllability, and more.
Reach out with your CV, publication list, and brief research interest statement.
Successful candidates will have published in top ML/NLP/CV venues (NeurIPS, ICLR, ICML, ACL, EMNLP, NAACL, CVPR, AAAI, etc.)
Topic
- MSCA-POSTDOCTORAL FELLOWSHIPS
Type
- POSTDOCTORAL FELLOWSHIP: Looking for Fellow
Similar opportunities
Project cooperation
Postdoc in multi-agent communication
- MSCA-POSTDOCTORAL FELLOWSHIPS
- POSTDOCTORAL FELLOWSHIP: Looking for Fellow
Yonatan Belinkov
Associate Professor at Technion - Israel Institute of Technology
Haifa, Israel
Project cooperation
- Proposal Idea
- Proposal under Development
- MSCA-POSTDOCTORAL FELLOWSHIPS
- POSTDOCTORAL FELLOWSHIP: Looking for Fellow
Oktay Cetinkaya
Lecturer in Sensor Systems at Newcastle University
Newcastle upon Tyne, United Kingdom
Project cooperation
Imagination in Cognition: Contemporary and Ancient Perspectives
- MSCA-POSTDOCTORAL FELLOWSHIPS
- POSTDOCTORAL FELLOWSHIP: Looking for Fellow
Kairi Herik
Senior Specialist for Personnel Recruitment at University of Tartu
Tartu, Estonia