Research Scientist - Foundation Model, Generative AI

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 - Research on unified multi-modal fundamental models including language, image and videos etc.

- Conduct cutting-edge research and development in computer vision and machine learning, especially in the areas of generative AI (e.g. image, video, or 3d generation).

- Transfer advanced technologies to Byte Dance products;

- Explore new products with artificial intelligence technology at its core.

Minimum Qualifications:

- 1-3 years of research and practical experience in one or more areas of computer vision, including but not limited to multimodal generation, such as text-to-image/video/3D generation and editing, and other related multimodal experiences - Strong knowledge of diffusion models and AR models, familiar with model architectures, theory and large scale training strategies.

- Familiar with various training modalities and ways to balance different modalities, to achieve stable training.

- Highly competent in algorithms and programming;
Strong coding skills - Work and collaborate well with team members.