Are you an ambitious researcher in computer science, who has experience with deep neural networks? Are you interested in tweaking the performance of such models on cutting-edge supercomputing technology? And would you like to contribute your skills to an exciting project that develops a foundation model for weather applications? Then we might have an attractive job offer for you. The Jülich Supercomputing Centre (JSC) is teaming up with the European Centre for Medium-range Weather Forecasting and 14 top institutions across Europe in the EU Horizon project WeatherGenerator. The WeatherGenerator will build a European generative foundation model of the Earth system that will serve as a new Digital Twin for Destination Earth. It will be based on representation learning and create a general and versatile machine learning tool that models the dynamics of the Earth system by training on a large variety of Earth system data. The WeatherGenarator will be task-independent and will improve results for a ride range of applications when compared to task specific machine learning tools.
AI Scientist – Foundation model for weather