PhD Position in Foundation Models for Multi-Agent Reinforcement Learning

Cph Ai Hub; Odense; Hybrid; DKK 360,000 - 480,000; Full time

Job summary

University of Southern Denmark invites applications for a PhD/Postdoc position in Odense M (Southern Denmark) focusing on foundation models for multi-agent reinforcement learning. The role targets students or interns exploring advanced ML techniques and real-world RL benchmarks.

Applicants should have a PhD or be close to completion, with strong proficiency in reinforcement learning and deep learning. The posting is listed via Jobindex and emphasizes a university & research track.

Qualifications

• PhD or PhD candidate in a relevant field (e.g., ML, AI, CS).
• Strong background in reinforcement learning and deep learning methods.
• Experience with academic research and publication is advantageous.

Responsibilities

• Conduct research on foundation models for multi-agent reinforcement learning.
• Develop experiments, analyze results, and reproduce findings.
• Collaborate with a research group and contribute to papers and presentations.

Skills

Reinforcement learning

Deep learning

Education

PhD or pursuing PhD

Job description

PhD Position in Foundation Models for Multi-Agent Reinforcement Learning

PhD / Postdoc University & research Universities & research Reinforcement learning Deep learning

PhD / Postdoc position in Odense M (Southern Denmark), at student / intern level. We classify it in the University & research track and under Universities & research. The ad asks for Reinforcement learning, Deep learning. Listed via Jobindex on 09 Nov 2026.

• Role: PhD / Postdoc
• Seniority: Student / intern
• Location: Odense M (Southern Denmark)
• Track: University & research
• Sectors: Universities & research
• Skills asked for: Reinforcement learning, Deep learning
• Employment: Full time
• Posted: 09 NOV 2026
• Listed via: Jobindex

Jobindex publishes the full advertisement. We index the posting and link to it rather than reproducing their text — everything above is our own reading.