Postdoc position: Statistical Data Science and Machine Learning for Climate Change Research

**About the project** --------------------- We are seeking a highly motivated and skilled individual to join the Statistical Data Science and Machine Learning Platform lead by Prof. Dr. David Ginsbourger (Institute of Mathematical Statistics and Actuarial Science) and Prof. Dr. Olivia Romppainen\-Martius (Climate Impacts groups, Institute of Geography) in the framework of the Oeschger Centre for Climate Change Research (OCCR). Of particular interest are developments in generative modelling, operator learning, amortized inference, and how recent advances in scientific ML can be leveraged in climate change research, e.g., by combining foundation models with diffusion models for local/specific downstream tasks. Application domains encompass climatology, meteorology, hydrology, and societal aspects of climate change research. **What you can expect** ----------------------- Together with the platform leads and members, the recruited person will actively engage in platform coordination and scientific animation activities, provide expertise and feedback to graduate students and other Early Career Researchers. Scientific animation may include crash\-courses on topics relevant to the platform and the recruited person. With a baseline affiliation in statistics, the recruited person will be encouraged to regularly visit and possibly be hosted (part time) in other OCCR groups depending on collaborations. Employment conditions and remuneration are in accordance with the standards of the University of Bern, Switzerland. **Profile of the candidate** ---------------------------- The successful candidate holds a PhD in statistics / ML / applied mathematics and has a strong interest in climate and weather applications, or he/she holds a PhD in climate or atmospheric science, meteorology or similar with an excellent background in statistics and ML. She/he has excellent programming and data handling skills, and a keen interest in interdisciplinary research. The candidate is p