Research associate (m/f/x)

The group conducts core research in artificial intelligence and machine learning, with a primary focus on online decision-making under uncertainty. Our work spans areas such as (inverse, deep, and causal) reinforcement learning, multi-armed bandits, and learning in multi-agent systems involving cooperation, competition, and coordination. We are particularly interested in how intelligent systems can adapt across changing domains and recover from suboptimal or biased decisions through principled approaches to domain adaptation and algorithmic recourse. While our methods are generic and applicable across diverse fields—including medicine, education, and finance—we primarily apply them to engineering and technical systems, such as the Internet of Things, next-generation communication networks, and robotics.

The researcher will work on the development of robust and efficient collective algorithmic recourse methods to enhance the resilience of mission-critical networked systems. The project lies at the intersection of machine learning, optimization, and multi-agent systems, addressing challenges arising from resource volatility and uncertainty in dynamic environments. The work will include both theoretical analysis—covering efficiency, scalability, and convergence—as well as the application of the proposed methods to optimize networked systems.