-
force fields (MLFFs) that combine state-of-the-art equivariant neural network architectures with robust, well-calibrated uncertainty estimates. These models will enable fully automated active learning in
-
of hybrid foundation model-graph neural network architectures for gene perturbation prediction, including the design and implementation of novel training strategies under experimental constraints, e.g
-
). The team focuses on the development and design of reliable, safe, and secure software systems, carrying out both upstream activities such as requirements quality assurance and architecture analysis, as
-
in the light of ongoing European projects. The candidate will play a central role in developing quantum communication protocols, designing quantum network architectures, and building SDN-enabled