Postdoc in Recursive Self-Improvement and Open-Ended Learning for AI
- Deadline
- Rolling · apply any time
- Location
- Basel, Switzerland
- Type
- Postdoc
- Working language
- English
- Posted
- 21 Nov 2026
- Verified
- 21 Nov 2026
About this opportunity
The Rhine AI group led by Prof. Ilija Bogunovic at the University of Basel's Department of Mathematics and Computer Science is hiring a full-time postdoc. You would lead research on recursive self-improvement and open-ended learning, where AI systems create their own tasks, environments and training procedures. Applications are reviewed on a rolling basis and the start date is flexible.
What is offered
- A full-time (100%) postdoctoral position in Basel, Switzerland.
- Room to shape and drive the group's research agenda in recursive self-improvement and open-ended learning.
- Research topics include LLM post-training with reinforcement learning, frontier learning, agentic RL environments, weight-space programming, world models and open-ended evolutionary search.
- Large-scale experiments with open LLMs and agents, with the aim of publishing at top venues such as ICML, NeurIPS and ICLR.
- Experience mentoring PhD students and working with national, international and industry partners.
- The posting describes the salary, benefits and working conditions as "excellent", but gives no figures.
- Flexible start date.
Who can apply
- You need a PhD in machine learning or a related field.
- You should have a strong publication record at leading machine learning venues.
- You need a solid grounding in mathematics and strong coding skills.
- You should have hands-on experience running large-scale experiments.
- Experience with LLM post-training, reinforcement learning, world models, generative modeling or evolutionary methods is a plus.
- You need to communicate very well in English.
How to apply
- Apply through the University of Basel online application portal, using the "Apply" link on the job page.
- Upload two PDFs: a motivation statement (no more than 150 words), and a CV that includes your publication list.
- Give contact details for your referees. Do not send recommendation letters.
- Also include either your PhD thesis or up to two representative publications.
- Applications are reviewed as they arrive, and the position stays open until a suitable candidate is found, so applying early is a good idea.
Requirements
-
Open to all nationalities
-
Early-career researcher
-
Minimum degree: PhD
Postdoc in Recursive Self-Improvement and Open-Ended Learning for AI
Rolling · No fixed deadline