The research of the Computational Intelligence Group ( addresses fundamental issues about how to design, use and understand autonomous machines that can evolve, learn and self-organise. We are interested in embodied intelligence that is not hosted in an abstract digital entity, but has a ‘body’ and agency that make it capable of acting in the world, generating its own experiences and learning from these experiences. To boost our research in learning machines we are looking for an assistant professor with the right background regarding the efficiency of learning algorithms. The overarching goal is to develop novel algorithms and models that solve learning problems with fewer learning trials and/or less data than currently possible and to validate these in a range of scenarios, varying from physical robots to conversational agents or data-sparse health settings. Possible approaches include combinations of knowledge-based and data-driven methods, surrogate models, sparse modelling and inference with discrete variables, sophisticated statistical or symbolic priors, multidimensional quality-diversity archives, and distributed or social learning approaches.