Develop novel state-of-the-art computer vision algorithms and corresponding systems, leveraging various deep learning techniques. Based on the project, help analyze and improve efficiency, scalability, and stability of corresponding deployed algorithms. Perform research that enables learning the semantics of data (images, video, text, audio, and other modalities), with strong emphasis on multimodality and open-world understanding. Collaborate with researchers and cross-functional partners including communicating research plans, progress, and results. Publish research results and contribute to research that can be applied to Meta product development.