Member of Technical Staff - AI Security

Build security environments, train adversarial agents, and evaluate frontier AI systems.Location: Tübingen / HybridEmployment: Full-timeThe roleYou will work across AI security, machine learning, and research engineering. You will design reinforcement-learning environments, train adversarial agents, and build evaluations for capable AI systems.What you ll work onDesign security environments for training and evaluating AI agentsPost-train agents using reinforcement learning and develop adaptive red-teaming methodsEvaluate frontier models and agentic systemsTurn research results into benchmarks, training methods, and toolsWhat we re looking forA strong track record in machine learning, security, or systemsStrong software and machine-learning engineering fundamentalsExperience with LLMs, agentic systems, or reinforcement learningAbility to run careful experiments and communicate results clearlyUseful experienceAI security, red teaming, or adversarial machine learningReinforcement learning or post-training for language modelsResearch engineering or production ML systemsPublished research or substantial open technical workWhat we offerCompetitive compensation with equityFlexible 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.