Senior Research Scientist, Intelligent Editing (Multimodality)

Work on intelligent editing and multimodal understanding within an AI research team focused on video/audio creation technology. Conduct cutting-edge R&D in computer vision and machine learning, including multi-modal understanding, vision-language tasks, and language model applications for downstream intelligent editing. Build and experiment with large-scale training approaches and RLHF, and help explore new AI-driven products. Collaborate across a technical team spanning CV, audio-video, and server/client engineering.