PhD stipend in Digital Twins and Hierarchical Multi-Agent Safe Reinforcement Learning.(DEIS)

This PhD stipend opportunity focuses on advanced research in Digital Twins and Hierarchical Multi-Agent Safe Reinforcement Learning. Candidates should have a strong foundation in reinforcement learning, particularly in safe reinforcement learning techniques that ensure reliable and secure agent behavior in complex environments. Expertise in multi-agent systems is essential, including the ability to model, simulate, and coordinate multiple autonomous agents operating hierarchically. Familiarity with Digital Twins technology is critical, involving the creation of virtual replicas of physical systems for real-time monitoring, simulation, and optimization. The role demands proficiency in machine learning frameworks and programming languages commonly used in AI research, such as Python and relevant libraries like TensorFlow or PyTorch. A solid understanding of control theory, system modeling, and simulation tools will be beneficial. The candidate should be prepared to engage in interdisciplinary research combining AI, systems engineering, and possibly domain-specific knowledge depending on the application area of the Digital Twins. Strong analytical skills, problem-solving abilities, and experience with experimental design and data analysis are important. Given the PhD level, a background in computer science, engineering, or related fields with rigorous training in AI and systems modeling is expected. This position is research-intensive and suitable for candidates aiming to contribute to cutting-edge developments in safe AI systems and digital simulation technologies.