Research Intern - Multimodal Foundation Model for Vision

**Research Intern – Multimodal Foundation Model for Vision**Sony AI is seeking research interns to join us. Our team mainly focuses on fundamental and applied research, with a focus on building next-generation foundation models for vision in a responsible manner. The role of a research intern is to develop efficient and effective methodologies and prototype solutions. You will work with a productive team of world-class scientists and engineers to tackle the most challenging problems in foundation models and generative AI, including low-cost yet powerful vision foundation models (VFM), vision-language models (VLM), unified models, automatic model compression, optimization and deployement on cloud and edge. You will see your ideas not only published in papers, but also improve the experience of billions of customers.**Roles and Responsibilities** PoC for various vision+text, generation relevant tasks (VQA, captioning, understanding, etc) and hardwares.**Required Qualifications and Skills** Better to have front-end development experience. Solid coding skills in Python, Pytorch, etc.**Working Location** Location flexible (Tokyo, Europe , US)# **Purpose**Fill the world with emotion, through the power of creativity and technology.# **Values****Dreams & Curiosity**Pioneer the future with dreams and curiosity.**Diversity**Pursue the creation of the very best by harnessing diversity and varying viewpoints.**Integrity & Sincerity**Earn the trust for the Sony brand through ethical and responsible conduct.**Sustainability**Fulfill our stakeholder responsibilities through disciplined business practices. #J-18808-Ljbffr