University of Amsterdam is looking for two PhD students interested in investigating geometric structure in data (e.g., structure of signals and shapes), machine learning architectures (e.g., group convolutional neural networks, graph neural networks, and representation embeddings), and scientific problems (e.g., with symmetry/equivariance constraints). You will employ the obtained insights to develop machine learning techniques that enable learning-based engineering for new data types and problems, and improve upon existing approaches on a fundamental level.