Senior Research Scientist, Intelligent Editing (Multimodality)

Lead cutting-edge research in computer vision and ML, focusing on multi-modal understanding, vision-and-language, and large-scale training. Advance state-of-the-art methods for video highlight detection, video slicing, and audio/music understanding. Develop intelligent editing capabilities by integrating language models into downstream tasks. Transfer research outcomes to products and explore AI-driven product concepts at scale. Publish results in top venues and collaborate with peers, mentoring junior researchers as needed. Demonstrate strong software engineering with Python and C++, delivering robust algorithms and scalable systems.