Job Details

The omni team at x. AI creates magical AI experiences beyond text, enabling understanding and generation of content across various modalities, including image, video, and audio. As a multimodal researcher/engineer, you will drive the models video generation capability through various aspects such as data, modeling, serving and product. You will work on both pretraining and posttraining and collaborate with product teams to push the frontiers of model capability as well as the end-to-end user experience. Focus Creating and driving research agenda to advance image and video generation and editing capabilities. Improving data quality, developing data filtering/generation techniques, and performing data study. Creating evaluation frameworks and internal benchmarks. Designing and implementing effective and efficient algorithms for achieving state-of-the-art model performance. Ideal Experiences Track record in leading research that significantly improves the capability and performance of ne...Video, Research, Engineer, AI, User Experience, Technology