The goal is to design and develop algorithms that not only achieve state-of-the-art performance in vision-language intelligence but also capture social, emotional, and behavioral dimensions of human experience. A central emphasis is on recognizing and explaining human skills, learning processes, and proficiency, enabling AI systems that are attuned to identity, diversity, and interaction while supporting human development and collaboration.
Requirements
- Strong background in machine learning for vision-language intelligence.
- Research experience in visual human behavior understanding, including human activity understanding
- Proficiency in deep learning frameworks (e.g., PyTorch, TensorFlow) and programming with Python.
- Working experience with HRI
Responsibilities
- Conduct research at the intersection of visual human behavior understanding, language, and human-centered AI.
- Develop models and algorithms that analyze and interpret human behavior, skills, and proficiency, including methods to recognize, represent, and explain task performance and learning.
- Design architectures that integrate visual and language modalities for behavior understanding, skill learning, knowledge transfer, and evaluation of human proficiency.
- Participate in multimodal data collection and annotation, with attention to behavioral, affective, and skill-related signals.
- Explore broad applications of vision-language intelligence in domains such as training, education, accessibility, and human-AI collaboration.
- Contribute to patents, academic publications, and prototypes that demonstrate both scientific impact and human-centered value.
Other
- Ph.D. or M.S. in computer science, electrical engineering, cognitive science, or a related field.
- Strong record of publications and communication skills for multidisciplinary collaboration.
- 2 - 5 years
