Fully funded PhD and Postdoc positions in LLM theory, mechanistic interpretability, efficient reasoning, and AI safety at Saarland University Saarland University in Germany

CRISTAL Lab at CISPA Helmholtz Center for Information Security in Germany is hiring for research openings in machine learning , LLM alignment , agentic AI , AI safety , robustness , continual learning , and benchmarking/evaluation . The post explicitly advertises PhD , postdoc , and intern opportunities, with a focus on building foundational science for safe, reliable, and context-aware AI. The lab emphasizes trustworthy AI research and related topics such as alignment, robustness, and evaluatio...

Inria is offering a postdoctoral research visit in neurosymbolic relational graph neural networks within the TYREX research team in France. The project sits at the intersection of computer science , graph neural networks , relational learning , and relational databases , with a strong focus on combining symbolic knowledge with message passing architectures. The research aims to move beyond purely statistical relational GNNs by injecting symbolic information such as schemas, constraints, function...

Andrew Lowy, Tenure-Track Faculty at CISPA Helmholtz Center for Information Security, is recruiting a PhD student or postdoctoral researcher to join his group in Saarbrücken, Germany . The position is centered on the mathematical foundations of machine learning , with interests in differential privacy , optimization , and machine unlearning . The post also highlights broader directions in AI safety and alignment , especially for candidates interested in rigorous theoretical work, proving fundame...

CRISTAL Lab at the CISPA Helmholtz Center for Information Security is hiring PhD students, postdocs, and interns in machine learning , LLM alignment , agentic AI , and AI safety . The lab, led by Cristina Garbacea, focuses on the foundational science behind safe, reliable, and context-aware AI systems, including principled alignment methods, robustness and safety guarantees, autonomous systems with long-horizon planning, continual learning, and benchmarking/evaluation. This opportunity is aimed ...

CRISTAL Lab (Communication, Reasoning, Intelligence & Safety for Trustworthy ALignment) at the CISPA Helmholtz Center for Information Security is recruiting for fully funded PhD positions , postdoctoral researcher positions , and research intern opportunities (BSc/MSc/PhD) in Germany . The lab focuses on trustworthy AI , especially AI alignment , agentic reasoning , foundation models , multi-agent systems , safety , robustness , evaluation , and transparent/adaptable intelligence . Research them...