We seek one Postdoctoral Researcher who will explore the introduction of weak lensing-specific constraints in deep learning models that prevent galaxy shape distortions, extending paradigms from optical methodologies to the radio domain. The effort will focus on large-scale reconstruction algorithms able to optimize the measurement of shape parameters from SKA interferometry through the coupling of deep-learning-based image priors with geometric shape regularization. The post-doctoral researcher will be located at the premises of FORTH with a strong collaboration with the CosmoStat Laboratory at CEA Saclay.