Research Intern - AI Security

Build security environments, adversarial agents, and evaluations for frontier AI systems.Location: Tübingen / HybridEmployment: InternshipThe roleYou will work across AI security, machine learning, and research engineering alongside the core team. You will take ownership of a technically ambitious project in agent security, from designing and implementing the approach to running experiments and communicating the results.What you ll work onDevelop and evaluate security environments, agent training methods, attacks, or defensesRun controlled experiments with clear baselines and verifiable outcomesAnalyze model behavior and communicate the results to the teamContribute code, evaluations, and research findings that remain useful after the internshipWhat we re looking forCurrent study or recent work in machine learning, computer science, security, or a related fieldStrong programming skills and experience building or evaluating machine-learning systemsCuriosity about AI agents and the discipline to investigate failures carefullyAbility to work independently and ask for feedback earlyUseful experienceLLMs, reinforcement learning, or agentic systemsAdversarial machine learning, red teaming, or AI safety evaluationsResearch codebases, reproducible experiments, or open-source contributionsA previous research project, thesis, or technical publicationWhat we offerCompetitive compensationFlexible hours and a remote-friendly setupVacation, learning, and conference budgetResearch freedom in a high-trust environmentWork with usSubmit your CV, a short note, and links to work that shows how you think and build using the application form.