Location: Lemont, IL
Cap-Exempt H-1B Position — No lottery required
Argonne National Laboratory, a U.S. Department of Energy national laboratory located near Chicago, Illinois, has an opening for a highly motivated term position in the Decision & Infrastructure Sciences Division. Machine learning (ML), specifically deep learning (DL) an AI foundation models, has demonstrated success in predicting weather for 1-14 days with skill on par with numerical weather prediction. Recently Argonne successfully implemented, AI foundation models for medium range weather forecasting (STORMER) and AERIS, a state-of-the-art Seasonal-to-sub-seasonal weather model AI model. A successful candidate will collaborate with this group to further develop AERIS, coupling the model with ocean and land components, data assimilation, multi-modality and regional refinement. In particular, this position will utilize generative AI transformer model to create a calibrated ensemble system for S2S at high resolution (30-km and finer) to deliver probabilistic weather forecasts beyond 14 days to allow for actionable, local-scale impacts on infrastructure and communities. The ideal candidate has a PhD in geophysical sciences, computer science, or machine learning with experience in developing and verifying deep learning-based models for large dynamical systems (e.g. weather). Some familiarity in data and model parallelisms for distributed training on large GPU-based machines is essential. who have experience with diffusion-based or other generative AI methods and multi-modal embeddings, as well as a background in atmospheric science, especially weather modeling. Responsibilities: - Contributes technical experience through analysis and support for programs and projects associated with machine learning, HPC, and computational problems related to earth system science and other dynamical systems. - Develops and evaluates machine learning/computational approaches, synthesis activities, computational tools, compiling results, contributes to reports, publications, and document