AMI Scientist - Geometry and 3D Vision

The role

You will work with a team on world model research efforts focusing on 3D geometry of the real world. This includes developing self-supervised learning methods, new architectures, and scalable algorithms for video data.

What you will do

• Develop self-supervised learning methods to learn from video and high-dimensional signals
• Create new architectures to predict world dynamics from video and high-dimensional signals
• Develop scalable algorithms for pre-processing and curating video data
• Create evaluations for benchmarking world model understanding, prediction, and planning
• Develop efficient algorithms for model-based planning and reasoning

Required qualifications

• 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 at least one of the following: 3D/4D reconstruction, SLAM or SfM, depth and pose estimation, point tracking
• Hands-on proficiency with a rendering or simulation engine (Blender, Isaac Sim, etc.), including scripted scene generation and batch rendering pipelines
• Demonstrated record of contributing to advanced research projects via publications and/or major model releases
• Experience developing evaluation frameworks for world models
• Experience releasing and maintaining open-source projects
• Proficiency in a deep learning framework (PyTorch or JAX)

About the company

ami is a global company with offices in Paris, Montreal, New York, and Singapore. They are building frontier world model-based AI systems that understand the real world, have persistent memory, can reason and plan, and are controllable and safe.