PhD Research Intern, Vision Language Action Models

Zoox • Boston, MA

1d • Onsite

About The Position

Zoox is transforming mobility with fully autonomous, electric vehicles designed from the ground up for a driverless future, aiming to make transportation safer, more sustainable, and accessible. The internship program offers hands-on experience with cutting-edge technology, mentorship, and opportunities to make meaningful contributions to real projects, seeking interns with strong academic performance, engagement beyond the classroom, intellectual curiosity, and a genuine interest in Zoox’s mission. This specific PhD Research Intern opportunity is within the Foundation Models team, which focuses on advancing the state of the art in autonomous driving, including Multimodal Language Action models (MLA) and massively scaling reinforcement learning for agent policies. The intern will work on the Multimodal Language Action model, exploring novel discrete action tokenization and flow matching approaches, building off of MotionLM, FAST and others. This involves training models at the billion+ scale on millions of miles of proprietary Zoox driving data, gaining valuable experience and insight into training MLAs at scale. This project is expected to contribute to publishable research and could be integrated into Zoox vehicles. Zoox is developing the first ground-up, fully autonomous vehicle fleet and its supporting ecosystem, operating at the intersection of robotics, machine learning, and design to provide next-generation mobility-as-a-service in urban environments.

Requirements

• Currently working towards a Ph.D., or advanced degree in a relevant engineering program
• Good academic standing
• Able to commit to a 12-week internship during one of the following summer 2026 cohorts: May 18th - August 7th OR May 26th - August 14th OR June 15th - September 4th
• At least one previous industry internship, co-op, or project completed in a relevant area
• Ability to relocate to the Bay Area, California (or Boston, Massachusetts) for the duration of the internship
• Interns at Zoox may not use any proprietary information they are working on as part of their thesis, any published work with their university, or to be distributed to anyone outside of Zoox
• Experience training VLMs, or VLAs
• Experience working in large codebases as part of a team
• Advanced understanding of Python and PyTorch
• Has authored publications in top ML/robotics conferences (e.g. NeurIPS, CVPR, ICRA, etc)

Nice To Haves

• Experience with autonomous driving
• Experience with machine-learning-based robotic planning
• Experience with large-scale, multi-node Pytorch workloads

Responsibilities

• Work on the Multimodal Language Action model
• Explore novel discrete action tokenization and flow matching approaches
• Build off of MotionLM, FAST and others
• Train models at the billion+ scale on millions of miles of proprietary Zoox driving data
• Contribute to publishable research

Benefits

• Monthly salary for this position is $9,500
• Medical insurance
• Housing stipend (relocation assistance will be offered based on eligibility)

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: Ph.D. or professional degree