Research Scientist, Intelligent Editing (Multimodality)

About the team
The Intelligent Creation Team is the AI, special effects, and audio-video creation technology team, responsible for the core technology and business development. It covers a variety of technical fields, including deep learning, computer vision, graphics, speech, recording and editing, special effects, client and server engineering, and provides cutting-edge content understanding, content creation, interactive experience, and consumption capabilities and industry solutions to other business lines within the company and external partners in various forms.

Responsibilities
1. Conduct cutting-edge research and development in computer vision and machine learning, especially in the areas of multi-modal understanding, vision and language, large-scale training, etc.
2. Transfer advanced technologies to ByteDance products;
3. Explore new products with artificial intelligence technology at its core.

Minimum Qualifications
1. At least 1 year of research and practical experience in one or more areas of computer vision, including but not limited to:
- Experience in multimodal understanding, such as video highlight detection and slicing, audio/music understanding, etc.
- Experience in vision and language, such as image/video captioning, retrieval, VQA, and other related fields.
- Experience with language models and apply them in various downstream tasks, especially for intelligent editing.
- Experience in large-scale training and RLHF.
2. Preferring candidates with publications in top-tier venues such as CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML or ACL, EMNLP, COLING, etc
3. Highly competent in algorithms and programming; Strong coding skills in C/C++ and Python.
4. Work and collaborate well with team members.
5. Ability to work independently.