AMI Scientist

What you'll do

• Develop self-supervised learning methods and architectures for learning world dynamics from video and other continuous signals.
• Build scalable algorithms for video preprocessing and curation, and evaluations for world-model understanding, prediction, and planning.
• Develop efficient algorithms for model-based planning and reasoning.

What they ask for

• Bachelor’s degree or equivalent experience in Computer Science or a related field.
• Proficiency in Python.
• Ability to design, run, and analyze experiments independently.
• Understanding of machine learning fundamentals, large-scale training, and accelerator-based (GPU or TPU) compute environments.

Nice to have

• Deep expertise in self-supervised learning, video and multimodal model architectures, or planning algorithms.
• Research contributions through publications and/or major model releases; experience with world-model evaluation, open-source projects, or PyTorch or JAX is also preferred.

Tools

Python, GPU, TPU, PyTorch, JAX

AI focus

Research and develop world models that learn from video and other high-dimensional signals to understand physical-world context, predict dynamics, and plan actions.