Magnetic confinement fusion may one day provide reliable, carbon-free energy, but the field currently faces major technical hurdles. Input from the Machine Learning (ML) community may play a key role in solving six key challenges: (1) disruption prediction, (2) simulation and dynamics modeling (3) resolving partially observed data, (4) improving controls, (5) guiding experiments with optimal design, and (6) enhancing materials discovery. For each problem, we give background, review past ML work, suggest features of future models, and list challenges and idiosyncrasies facing ML development. We also discuss ongoing efforts to update the fusion data ecosystem and identify opportunities further down the line that will be enabled as fusion and its data infrastructure advance. We intend this position paper to serve as an entry point for ML practitioners interested in supporting magnetic nuclear fusion research.