Research Scientist, Models Autonomous Vehicles

Human Interactive Driving – Human Interactive Driving /

At Toyota Research Institute (TRI), we’re on a mission to improve the quality of human life. We’re developing new tools and capabilities to amplify the human experience. To lead this transformative shift in mobility, we’ve built a world-class team in Energy & Materials, Human-Centered AI, Human Interactive Driving, Large Behavior Models, and Robotics.

Within the Human Interactive Driving division, the Extreme Performance Intelligent Control department is working to develop scalable, human-like driving intelligence by learning from expert human drivers. This project focuses on creating a configurable, data-driven world model that serves as a foundation for intelligent, multi-agent reasoning in dynamic driving environments. By tightly integrating advances in perception, world modeling, and model-based reinforcement learning, we aim to overcome the limitations of more compartmentalized, rule-based approaches.

The end goal is to enable robust and adaptable, driving policies that generalize across tasks, sensor modalities, and public road scenarios—delivering ground-breaking improvements for ADAS, autonomous systems, and simulation-driven software development.

We are seeking a highly motivated Research Scientist specializing in uncertainty-aware world models for autonomous vehicles. In this role, you will develop cutting-edge models that enable autonomous systems to perceive, predict, and interact intelligently with their environment. You will work at the intersection of machine learning, computer vision, robotics, and probabilistic modeling to build robust world models that improve perception, planning, and decision-making in self-driving systems.

• Develop and refine world models that improve the understanding of sophisticated and dynamic driving environments.
• Research and implement deep learning, reinforcement learning, and probabilistic modeling techniques for improved scene representation and prediction.
• Design algorithms that integrate sensor fusion, temporal reasoning, and uncertainty estimation to improve autonomous vehicle behavior.
• Collaborate with cross-functional teams, including perception, planning, and simulation engineers, to develop real-time, scalable models for deployment.
• Conduct experiments, simulations, and real-world validations to assess the effectiveness of world models.
• Publish research findings in premier conferences and journals and contribute to the AI and robotics research community.
• Stay up to date with advancements in machine learning, generative modeling, and simulation technologies.

• Ph.D. (or equivalent experience) in Machine Learning, Computer Science, Robotics, or a related field.
• Strong background in probabilistic modeling, reinforcement learning, and deep learning architectures (e.g., Transformers, VAEs, Diffusion Models).
• Strong understanding of Bayesian inference, state-space models, and uncertainty quantification.
• Hands-on experience with world models, predictive modeling, or generative modeling in robotics or autonomous systems.
• Prior experience in publishing research at NeurIPS, ICML, CVPR, ICRA, or similar.
• Proficiency in Python and ML frameworks (Tensor Flow, PyTorch, JAX).
• Experience working with autonomous vehicle datasets, sensor modalities (LiDAR, camera, radar), and simulation environments.
• Excellent problem-solving skills and the ability to work in a fast-paced team research environment.

Please reference this Candidate Privacy…