Your role

The successful candidate will join the SERVAL research group and contribute to research and development activities at the intersection of Agentic AI, AI Security, Trustworthy AI, Software Engineering, and Cybersecurity. The group is developing novel methods, tools, and platforms to support the safe deployment of AI systems in real-world environments. Current research activities focus on topics such as:

• AI agents and computer-use agents
• Security, robustness, and trustworthiness of AI systems
• Evaluation, benchmarking, and testing of AI systems
• Runtime monitoring and governance of AI agents
• Formal specification and verification techniques for AI-enabled systems
• AI systems for enterprise and cybersecurity applications
• AI compliance, risk assessment, and trustworthy AI engineering

The candidate will contribute to both fundamental research and the development of practica...