PhD Positions in AI Safety at ELLIS Institute Tübingen

Join the ELLIS Institute Tübingen and MPI-IS for PhD positions and research opportunities in AI safety and alignment.

Applications are invited for PhD students, interns, master thesis students, research assistants, and postdocs at the ELLIS Institute Tübingen and MPI-IS to work on AI safety and alignment.

The research group focuses on developing algorithmic solutions to reduce harms from advanced general-purpose AI models, particularly alignment of autonomous LLM agents.

• Rigorous AI evaluations
• Informing the public about risks and capabilities of frontier AI models
• Understanding how AI models generalize

To apply, please fill this Google form.

Tags: AI safety, PhD positions, ELLIS Institute Tübingen, MPI-IS, AI alignment, LLM agents, AI research