AMI Scientist/Interns - Geometry and 3D Vision

What you'll do

• Develop self-supervised methods and architectures for learning and predicting world dynamics from video and other high-dimensional signals.
• Build scalable video preprocessing and curation algorithms, 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 GPU or TPU compute environments.

Nice to have

• Deep expertise in 3D/4D reconstruction, SLAM or SfM, depth and pose estimation, or point tracking; or hands-on proficiency with a rendering or simulation engine such as Blender or Isaac Sim.
• Research contributions through publications or major model releases; experience with world-model evaluation, open-source projects, or PyTorch or JAX.

Tools

Python, GPU, TPU, Blender, Isaac Sim, PyTorch, JAX

AI focus

Advances world-model AI that learns from video and other high-dimensional signals to understand physical-world context, predict dynamics, and plan actions.