PhD Research Intern, Vision Language Action Models

About Zoox Zoox is transforming mobility with fully autonomous, electric vehicles designed from the ground up for a driverless future. Our mission is to make transportation safer, more sustainable, and accessible to everyone. At Zoox, innovation, collaboration, and a bold vision for the future drive everything we do. About Our Internship Program Zoox’s internship program offers hands-on experience with cutting-edge technology, mentorship from some of the industry’s brightest minds, and the opportunity to make meaningful contributions to real projects. We seek interns who demonstrate strong academic performance, engagement beyond the classroom, intellectual curiosity, and a genuine interest in Zoox’s mission. Project OverviewThis internship opportunity is within the Foundation Models team which focuses on advancing the state of the art in autonomous driving: Multimodal Language Action models (MLA), massively scaling reinforcement learning for agent policies, and more.  You will have the chance to work on our Multimodal Language Action model, exploring novel discrete action tokenization and flow matching approaches, building off of MotionLM, FAST and others. You’ll train models at the billion+ scale on millions of miles of proprietary Zoox driving data. You’ll gain valuable experience and insight into training MLAs at scale. This project will contribute to publishable research, and could make it into our vehicle.