PhD Position: Toward Trustworthy and Adaptive Agentic AI Systems

We are looking for a highly motivated PhD candidate to join the Machine Learning Group at the Bernoulli Institute, University of Groningen. This position focuses on building trustworthy and adaptive agentic AI systems that can plan, reason, and learn continually in complex, open-ended environments. The research will address fundamental challenges in three interconnected areas: 1. **Planning & Reasoning** — Developing agents that can compose multi-step plans, leverage structured knowledge, and reason under uncertainty in dynamic settings. 2. **Safety & Alignment** — Designing mechanisms for safe exploration, robust decision-making, and alignment with human values, ensuring agents behave reliably in high-stakes domains. 3. **Continual Learning** — Enabling agents to acquire new capabilities over time without catastrophic forgetting, adapting to distributional shifts and evolving task requirements. The position is fully funded for four years and includes travel budget for international conferences (NeurIPS, ICML, ICLR, AAMAS, etc.).