Two PhD Positions in AI for Science at the University of Amsterdam

Doctorat / PhD Type de contrat : TEMPORARY Date limite de candidature : 2027-01-15T23:59:59+01:00

Curious how foundation models can accelerate environmental science, and how they reach their answers? Join Us! Foundation models are changing how science is done. To truly help scientists, they must work with real scientific data, and we must understand how they reach their answers. That is the challenge you will take on. We are looking for two PhD candidates (four years each) to make AI both useful and understandable for science. You will join a collaborative team at the University of Amsterdam, led by Prof. Evangelos Kanoulas and Dr. Ana Lucic, and work closely with AI researchers and environmental scientists across Europe in the Horizon Europe project EVELYN. Together, we will turn cutting-edge AI into tools that help researchers understand and reduce environmental pollution. This is what you will do Position 1: Fine-tuning and retrieval for multimodal foundation models in science Foundation models change how science is done: one model, pre-trained on broad data, can be adapted to many specialised tasks. Scientific tasks rarely look like a chat, though. Scientists need detection maps from satellite imagery, fast approximations of expensive simulations, gap-filled sensor records and ranked candidate explanations, each backed by evidence. In this position you develop and evaluate methods that adapt multimodal foundation models to such tasks and ground their predictions in retrieved data and knowledge. You work with real EVELYN use cases (air quality, PFAS, microplastics, soil and water contamination, satellite detection of oil spills and plastic) and with the environmental scientists who will use the models. You will be part of the Information Retrieval Lab (IRLab) at the Informatics Institute. What are you going to do? We are looking for an enthusiastic and creative individual who is interested in: Developing parameter-efficient methods that adapt foundation models to scientific tasks with diverse outputs, from segmentation maps to simulation fields and time series. Developing automatic methods that decide where and how to adapt a model within a compute budget, for image, atmospheric and time-series models. Developing retrieval-augmented models that use past observations, simulations and scientific literature to improve and justify their predictions. Designing evaluation frameworks that compare foundation models fairly against strong specialist baselines and test whether outputs are supported by evidence. Working with environmental scientists to turn their questions into machine learning tasks. Publishing and presenting your findings at international AI conferences such as ICLR, SIGIR, ACL and EMNLP. The exact topics and the work plan are defined together with the selected candidate. Position 2: Mechanistic interpretability of machine learning models As machine learning (ML) models gain influence on everyday life, it becomes increasingly…