Rainmaker Fellow, Machine Learning

Summary

Develops and evaluates machine-learning models and reproducible datasets from sensor, radar, satellite and NWP data to address atmospheric forecasting, retrieval, and operational decision problems for precipitation-enhancement programs. Builds baselines, trains and validates models with attention to calibration, uncertainty, and failure modes, works closely with atmospheric scientists to define targets and physical constraints, and delivers durable artifacts such as benchmark datasets, prototype models, evaluation reports, or research papers.