Job Description

About the team
The Seed Vision team focuses on foundational models for visual generation, developing multimodal generative models, and carrying out leading research and application development to solve fundamental computer vision challenges in GenAI.

Responsibilities
- Develop and scale vision foundation models across image and video modalities.
- Design data pipelines, pre-training strategies, and post-training methods for vision tasks.
- Improve core capabilities such as perception, reasoning, and multimodal understanding.
- Optimize model architectures, training efficiency, and evaluation frameworks.
- Explore real-world applications of vision models in multimodal systems.

The base salary range for this position in the selected city is $212800 - $387600 annually.