PhD & Postdoc Positions in Trustworthy AI and Alignment (m/f/d) - CRISTAL Lab

The research group of Dr. Cristina Gârbacea is actively recruiting fully funded PhD Students, Postdoctoral Researchers, and Interns (BSc/MSc/PhD) to join CRISTAL Lab at CISPA! Her research focus includes:

• LLM Alignment: Developing principled, scalable methods ensuring foundation models align with human intent and diverse preferences.
• AI Safety & Robustness: Building verifiable alignment mechanisms, safety guarantees, and defenses against failures and adversarial exploits.
• Agentic AI & Continual Learning: Investigating autonomous reasoning systems capable of long-horizon planning and tool use without safety drift.
• Benchmarking & Evaluation: Creating contamination-resilient environments to accurately measure evolving capabilities and real-world alignment.

"CRISTAL lab's mission is to develop cutting-edge AI systems that can communicate effectively, reason reliably, operate safely in complex environments, and make transparent and trustworthy decisions. We are focused on pushing the boundaries of AI alignment, reasoning, safety evaluation, and interpretability."

CRISTAL Lab
CISPA Helmholtz Center for Information Security

If you wish to be part of CRISTAL Lab's next breakthrough, please follow the application guidelines carefully and submit all the required documents in our application form.

Note: Intern positions are available and can be applied to here.