We announce a fully-funded 2 year postdoctoral researcher position in Multimodal Deep Learning at Uppsala University, Sweden. Multimodal Vision-Language models integrate computer vision and natural language processing techniques to process and generate information that combines both visual and textual modalities, enabling a more profound understanding of the content within images and videos. Vision-language models exhibit promising potential, and there are several important research challenges to explore. Effective integration of both modalities (vision and language), and aligning visual and text embeddings into a cohesive embedding space continue to pose significant challenges. In this project, the successful candidate will conduct fundamental research and methods development towards designing efficient multimodal models and exploring their applications in computer vision. We are looking for a candidate with a deep learning background and an interest in working on the subject of vision-language modeling. The application areas of interest will be decided in a dialogue between the candidate and the supervisor, taking into account the candidate's interests and research proposal. The position also offers teaching possibilities up to 20%, in English or Swedish. The selected candidate will work in the Department of Information Technology, Division of Systems and Control, in Ekta Vats’ group and the Beijer Laboratory for Artificial Intelligence Research. The project offers a rich collaborative environment (spanning theoretical ML research together with partners at the SciML group), with participation in leading CV/ML conferences (ICML, NeurIPS, CVPR, ICCV, etc.) being expected.