We seek a creative and highly motivated scientist to conduct innovative research that integrates machine learning (ML), artificial intelligence (AI), and advanced data assimilation techniques into next-generation analysis and forecasting systems for numerical weather prediction. This position will focus on developing and evaluating novel approaches that enhance the assimilation of remote sensing products, such as all-sky radiances and aerosol retrievals, within the NSF NCAR’s community coupled data assimilation (DA) systems such as MPAS-GOCART2G-JEDI, MPAS-DART, or WRF-Chem/WRFDA in the Mesoscale and Microscale Meteorology (MMM) laboratory. The scientist will be encouraged to explore and prototype new ML/AI approaches, even without extensive prior AI experience, provided they have a strong foundation in numerical modeling, data processing, or data assimilation theory. Example research areas include, but are not limited to, ML-based observation pre- or post-processing, surrogate observation operators, adaptive quality control (QC) or error modeling, efficient handling of large satellite data pipelines, and hybrid ML-DA methods to improve analysis accuracy and computational efficiency (e.g., multi-scale localization and/or inflation). The scientist will also contribute to advancing our coupled DA systems and end-to-end cycling workflow within the DA framework. As part of team efforts, activities may include incorporating ML/AI components into existing DA infrastructure, integrating high-volume remote sensing datasets, evaluating novel algorithms within cycling experiments, and developing tools that enhance system scalability and scientific impact. The scientist will work both independently and collaboratively in a multidisciplinary research environment, developing and implementing research plans, analyzing results with rigorous scientific interpretation, and publishing findings in peer-reviewed journals. This position offers strong support for innovative exploration and provides opportunities to shape the future of satellite DA and AI-enabled environmental prediction.