Sort by
Refine Your Search
-
networks. Participation in national and internationally funded research projects. Contribution to advanced digital twin and agent-based simulation platforms. Opportunities for interdisciplinary collaboration
-
to advanced digital twin and agent-based simulation platforms. Opportunities for interdisciplinary collaboration across engineering and computer science domains. A supportive environment for academic
-
candidate will develop and test novel user interfaces that integrate state-of-the-art Large Language Models (LLMs) with novel logic-based multi-robot planning algorithms. This work will be evaluated through
-
with natural language. The successful candidate will develop and test novel user interfaces that integrate state-of-the-art Large Language Models (LLMs) with novel logic-based multi-robot planning
-
fragmentation. This project seeks to overcome these barriers by integrating BIM-based energy modeling, semantic data models (Ontologies), and Large Language Models (LLM) into the control workflow. The candidate
-
mechanisms rather than solely measuring effects. Central methodological capabilities could include: Simulation and system modelingsuch as discrete-event simulation, agent-based modeling, and system dynamics
-
, ablations), including simulator- or metamodel-generated rollouts. Implement, test, and benchmark RL methods for policy discovery (e.g., multi-agent, multi-objective, uncertainty-aware, and/or safe RL), and
-
complex materials simulations. These agents will assist with setting up, executing, and optimizing electronic structure workflows, from standard ground-state Density Functional Theory (DFT) calculations
-
Bayesian Networks (DBNs) for probabilistic risk modelling Scenario-based simulation for rare-event analysis You will be part of a dynamic, interdisciplinary research setting at one of Europe’s leading
-
be considered an advantage if you have experience with safety-critical systems, multi-agent autonomy, or learning-based/data-driven/robust/adaptive control under uncertainty, supported by strong