PhD in Recursive Self-Improvement and Open-Ended AI Learning
- Deadline
- Rolling · apply any time
- Location
- Basel, Switzerland
- Type
- PhD Position
- Duration
- 48 months · 4 years
- Working language
- English
- Posted
- 21 Nov 2026
- Verified
- 21 Nov 2026
About this opportunity
The Rhine AI group, led by Prof. I. Bogunovic in the Department of Mathematics and Computer Science at the University of Basel, is hiring PhD students to work on recursive self-improvement (RSI) and open-ended learning. This research looks at AI systems that create their own tasks, environments and training procedures. These are full-time, four-year positions with a flexible start date, in a growing group funded by a recent ERC Starting Grant and an SNSF grant.
Research topics
- Reinforcement learning post-training of large language models
- "Frontier learning" and building RL environments for agentic tasks
- Weight-space programming and world models
- Open-ended evolutionary search
What is offered
- A full-time (100%) PhD position for 4 years, the standard length of a PhD in Switzerland
- Salary, benefits and working conditions that the posting calls "excellent" (no figure is given)
- Compute for large-scale experiments, including the lab's own GPU servers and access to national supercomputing
- Close supervision and mentoring, with national and international collaborators
- Funding for conference travel
- Life in Basel, where Switzerland, France and Germany meet
- A flexible start date
Who can apply
- You need a Master's degree in computer science, mathematics, physics or a related field
- An exceptional academic record and a solid grounding in mathematics
- Strong coding and implementation skills, including running large-scale experiments
- Experience with LLMs, reinforcement learning, generative modelling or evolutionary/open-ended methods is a plus
- Research experience helps but is not required
- Excellent communication skills and fluent spoken and written English
How to apply
Apply through the University of Basel's online career portal. Upload two PDF files that together contain:
- A motivation statement of no more than 150 words
- Your CV, with publications if you have any
- Scanned transcripts from your bachelor's and master's degrees
- Contact details for your referees (do not send recommendation letters)
- Your latest thesis and/or a publication, if available
There is no fixed deadline. Applications are reviewed as they arrive, and the positions stay open until suitable candidates are found, so it is best to apply early.
Requirements
-
Open to all nationalities
-
PhD candidate
-
Minimum degree: Master's
PhD in Recursive Self-Improvement and Open-Ended AI Learning
Rolling · No fixed deadline