Computer Vision Researcher

Main mission

Advances the interpretation of images, videos, and 3D scenes.

5 key responsibilities

• Develop new visual perception architectures.
• Study 3D, video, real-time, and multimodal image-text.
• Build domain datasets and reference benchmarks.
• Publish and compare results to the global state of the art.
• Transfer models to applications: health, industry, mobility.

Key skills

Vision Transformers, diffusion, 3D, PyTorch, image mathematics.

What's expected

Push the boundaries of what machines can see and understand, with reproducible results.

Career paths

Vision Research Lead, Senior Vision Engineer, Multimodal Researcher.