Internship Multimodal AI for Video Understanding (m/f/x)

Job description

Welcome to ZEISS – a company that combines innovation and responsibility! Our corporate functions are diverse and make a decisive contribution to the strategic orientation and sustainable success of ZEISS. Your role: At ZEISS Corporate Research & Technology, we are offering student positions (internship and/or master’s thesis) in the area of multimodal AI and video understanding. You will work on research problems at the intersection of vision, language, and structured data, with a focus on developing models that can understand complex real-world scenarios such as surgical workflows The goal is to move beyond frame-level analysis towards holistic, temporally consistent representations that integrate multiple sources of information Your tasks Contribute to research on multimodal and video-based machine learning methods, develop and evaluate models for holistic video understanding (e.g. video-language models, temporal reasoning, multimodal fusion) Work with real-world datasets and problem settings from ZEISS applications, implement and analyze state-of-the-art approaches and extend them in a research-driven setting Your profile: Enrolled in a Master’s or PhD program in Computer Scien...