Research Intern, AI Security
Exponential Security LabsTübingen, Germany
AI safety & policy
Information security
Internship
AI safety & policy
Information security
Internship
Routes to impact
Testing your fit for a certain career path
Direct high impact on an important cause
Description
Build and evaluate AI security environments, adversarial agents, and experiments for frontier AI systems.
- Develop security environments, agent training methods, attacks, and defenses
- Design and run controlled experiments with clear baselines and verifiable outcomes
- Analyze model behavior and communicate findings to the team
- Contribute reusable code, evaluations, and research outputs from an ambitious agent security project
This text was generated by AI. If you notice any inconsistencies, please let us know using this form.
