Job description
University of Stuttgart • Stuttgart, Germany
Stuttgart, Germany
- In this role, you'll conduct PhD research in AI safety, empirically investigating large language models to understand novel behaviours and ensure safe AI development.
- Evaluate capabilities and discover deceptive behaviours in frontier AI systems and agentic settings.
- Investigate research questions related to evaluation awareness and agent behaviour in large reasoning models.
- Publish your findings in leading academic journals and present work at conferences.
- Work within a research group dedicated to identifying safety and security vulnerabilities in AI technologies.
Applications are handled by the employer.
AI Safety Careers does not process applications directly.