Automated Driving Advanced Development Intern, Machine Learning Research

The Team

The Automated Driving Advanced Development division bridges TRI research and Toyota products. In partnership with Woven by Toyota, the team is researching and developing an end-to-end learned driving stack that maps sensor inputs directly to planned trajectories.

The Internship

We are seeking a research intern to investigate foundation models and generative AI for autonomous driving. You will work with TRI researchers to define and pursue a research question aligned with your interests and the team's ongoing work. Potential directions include multimodal reasoning and agents; generative models for action, world modeling, and simulation; and learning and evaluation through interaction.

You'll lead an independent research project shaped around your interests and the team's ongoing work. Potential directions include language and vision-language models, coding agents, generative driving policies, world models and simulation, and learning from closed-loop feedback. You'll work with Toyota driving data and closed-loop simulation infrastructure, with the goal of producing work suitable for a research paper submission.

The Opportunity

As a research intern on AD2, you will own a standalone research project in sim-to-sim and sim-to-real domain mapping, with the opportunity to:

• Drive your own research: Shape the approach, run experiments, and analyze results, with the independence to set your own direction.
• Publish your findings: The project is designed to produce results suitable for publication.
• Shape a real autonomy model: The tools and insights you create will help the team improve our autonomy models, with the potential to influence the autonomy stack eventually deployed in Toyota vehicles.
• Collaborate with experienced researchers: Work closely with a small team of industry-leading researchers with deep experience in robotics and autonomous driving.
• Work at scale: Use the same large-scale Toyota driving data, base models, and simulation infrastructure the team uses every day.

Responsibilities

• Define a focused research question and experimental plan with your mentor, informed by your interests and the team's research priorities.
• Develop methods in one or more relevant areas, such as multimodal agents, generative policies, world models, simulation, or learning from interaction.
• Build research prototypes using open-source datasets, large-scale Toyota driving data, the team's closed-loop simulation infrastructure.
• Design experiments and evaluate generalization, robustness, efficiency, or closed-loop behavior, as relevant to the project.
• Collaborate with TRI researchers and engineers to analyze results, investigate failure modes, and refine the research approach.
• Communicate findings through reproducible experiments, research presentations, and technical writing, including publication contributions where appropriate.

Qualifications

• Currently pursuing a Ph.D. or master's degree in Computer Science, Robotics, Machine Learning, Artificial Intelligence, Electrical Engineering, or a related field.
• Proficiency in Python and ML frameworks such as PyTorch for implementing and evaluating research ideas, along with an understanding of version control, testing, and software engineering fundamentals.
• Research experience in one or more of the following: computer vision, natural language processing, generative modeling, reinforcement learning.
• Demonstrated research ability, such as publications, preprints, or substantial independent research projects.
• Ability to work independently on an open-ended research problem, and to communicate methods and results clearly.
• Able to work in a hybrid in-office arrangement at TRI's headquarters in Los Altos, California, for the full 12-week internship.

Bonus Qualifications

• Experience with driving or robotics simulators such as CARLA or with neural rendering.
• Experience with language or vision-language models, agent systems, or multimodal reasoning.
• Experience with diffusion or flow models, generative policies, video generation, or world models.
• Experience working with real-world sensor data, such as video, lidar, IMU, or radar.
• Experience with autonomous driving, robotics, simulation, or closed-loop learning and evaluation.
• Publications at venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, CoRL, ICRA, RSS.