Member of Technical Staff — ML Research, Multimodal

What you'll do

• Design and implement model architectures and training algorithms for massive, multimodal physical data.
• Address modeling challenges including irregularly sampled modalities, long-horizon rollouts, and probabilistic forecasting.
• Run experiments and ablations, and work across data, model, evaluation, and infrastructure to scale training.

What they ask for

• Strong grasp of machine-learning fundamentals and depth in at least one relevant domain.
• Experience training large-scale models and analyzing experimental results through ablation studies.
• Familiarity with distributed training and the systems considerations of scaling models.
• Track record of turning open-ended research problems into production models.

AI focus

Develops a Large Physics foundation Model to predict the evolution of physical systems, starting with weather, using multimodal physical observations.