Tri2mo ago

ML Research Engineer, Interpretable AI for End-to-End Automated Driving

United States·Los AltosFull-timemid

EngineeringData ScienceOtherMl Research Engineer

3 views0 saves0 applied

Apply Now

Quick Summary

Overview

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.

Technical Tools

cpppythonab-testingdeep-learningmachine-learning

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 advancing the state of the art in AI, robotics, driving, and material sciences.

The Team

The Automated Driving Advanced Development (AD2) division at TRI will focus on enabling innovation and transformation at Toyota by building a bridge between TRI research and Toyota products, services, and needs. We achieve this through partnership, collaboration, and shared commitment. This new division is leading a new cross-organizational project between TRI and Woven by Toyota to conduct research and develop a fully end-to-end learned driving stack. This cross-org collaborative project is harmonious with TRI’s robotics divisions' efforts in Diffusion Policy and Large Behavior Models.

Within AD2, we are pursuing a focused research effort in Interpretable AI (iAI) for end-to-end learned automated driving systems, tightly coupled with AD2’s work on Large Behavior Models (LBM-Drive) and World Foundation Models (WFM), while remaining architecturally and product independent.

The Opportunity

We are seeking a Machine Learning Researcher to contribute to research on interpretable AI methods for learning-based automated driving systems. This role is ideal for a researcher who enjoys hands-on experimentation, model development, and evaluation, and who wants to work on foundational problems at the intersection of autonomy, interpretability, and safety. You will work closely with senior researchers and engineers to develop methods that make end-to-end neural driving policies more interpretable, diagnosable, and verifiable, while preserving performance and scalability. Your work will contribute to building “glass-box” representations that help engineers and researchers better understand, debug, and validate learned driving behaviors.

Conduct research on interpretable AI methods for end-to-end learned automated driving policies, under the guidance of senior and staff researchers.

Develop and evaluate structured representations of driving behavior, such as interpretable behavioral modes underlying learned neural policies.

Implement methods that associate driving behavior with perceptual and contextual cues, including language-based or symbolic explanations where appropriate.

Design and run experiments using large-scale learned policies and simulation infrastructure to assess interpretability, diagnostic value, and failure modes.

Contribute to evaluations of explainability methods for debugging, validation, and analysis of learned driving systems in simulation and/or controlled datasets.

Collaborate with researchers and engineers across AD2, LBM, and WFM teams to integrate xAI ideas into broader research workflows.

Document research findings clearly and contribute to internal reports, technical presentations, and peer-reviewed publications.

Stay up to date with advances in interpretable AI, representation learning, generative models, and embodied AI research.

Master's or PhD or equivalent research experience in Machine Learning, Robotics, Computer Vision, or a related quantitative field.

A demonstrated ability to conduct independent research and contribute to peer-reviewed publications at leading venues (e.g., NeurIPS, ICML, ICLR, CVPR, CoRL, RSS, ICRA).Strong foundation in modern machine learning, including deep learning, representation learning, and sequence or policy modeling.

Experience implementing and evaluating ML models using Python (and familiarity with C++ in research or experimental contexts).

Interest in or experience with end-to-end learning approaches for robotics or autonomous systems.

Ability to work effectively in collaborative, cross-disciplinary research environments.

Strong written and verbal communication skills.

Experience with interpretable AI, or model introspection techniques.

Familiarity with structured or hybrid models (e.g., latent-variable models, program induction, or discrete representations).

Experience evaluating learning-based systems in closed-loop simulation or real-world embodied settings.

Background in automated driving, robotics, or safety-critical AI systems.