Eventual, based in San Francisco, is seeking a Research Engineer for the Visual Understanding team. In this role, you'll manage visual understanding capabilities to transform vast video datasets into usable training data. Responsibilities include training multimodal models, designing efficient data taxonomies, and collaborating closely with research labs. Ideal candidates will have experience in perception tasks, familiarity with cutting-edge models, and a strong bias towards efficient data processing, all while being part of a small, dynamic team that works four days a week in the office. #J-18808-Ljbffr Consider building your career as a Research Engineer, Visual Understanding for Multimodal AI at Eventual. Our organisation is growing, and we are hiring a Research Engineer, Visual Understanding for Multimodal AI in San Francisco, CA, United States. This opening is for the Research Engineer, Visual Understanding for Multimodal AI role at Eventual.