Research Scientist - World Model

What you'll do

• Invent world-model architectures and mechanisms for action conditioning, view conditioning, and long-horizon rollouts.
• Define evaluation metrics and run scaling studies across compute, data, and architecture.
• Publish research and contribute to an open-source release.

What they ask for

• PhD or equivalent research record in ML, computer vision, robotics, or a related field.
• Deep expertise in large-scale generative modeling, self-supervised representation learning, or model-based RL.
• Strong PyTorch and large-scale, multi-node training experience.
• Top-venue publications and/or widely used open releases.

Nice to have

• Prior work on world models, model-based RL, generative video, neural simulation, or 4D scene representations.
• Experience using generative models for embodied tasks such as planning, control, or evaluation.

Tools

diffusion, transformer, autoregressive, PyTorch

AI focus

Research and develop generative world models that are interactive, controllable, physically faithful, and useful for embodied reasoning and policy training.