Senior Research Scientist, Large Behavior Models

Toyota Research Institute•Cambridge, MA

About The Position

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 ground-breaking shift in mobility, we’ve built an extraordinary team in Automated Driving, Energy & Materials, Human-Centered AI, Human Interactive Driving, Large Behavioral Models, and Robotics. The Mission Make general-purpose robots a reality. The Challenge We envision a future where robots assist with household chores and cooking, aid the older population in maintaining their independence, and enable people to spend more time on the activities they enjoy most. To achieve this, robots need to be able to operate optimally in messy, unstructured environments. Our mission is to answer the question “What will it take to create truly general-purpose robots that can accomplish a wide variety of tasks in settings like human homes with minimal human supervision?”. We believe the answer lies in cultivating large-scale datasets of physical interactions from diverse sources and using the latest advances in machine learning to learn general-purpose robot behaviors from them. The Team Our goal is to revolutionize the field of robotic manipulation, enabling long-horizon dexterous behaviors to be efficiently taught, learned, and improved over time in diverse, real-world environments. Our team has deep multi-functional expertise across hardware, simulation, perception, controls, and machine learning, and we measure our success in terms of fundamental capabilities' development, as well as research impact via open-source software and publications. Our north star is fundamental technological advancement in building robots, which can flexibly perform a wide variety of tasks in diverse environments with minimal human supervision. Come join us and let’s make general-purpose robots a reality. Some of our ongoing work is highlighted here. The Opportunity We’re looking for a driven research scientist or research engineer with a strong background in embodied machine learning and a “make it happen” mentality. The ideal candidate is able to work independently when needed, but works well witha larger integrated group at the latest of state-of-the-art robotics and machine learning. Experience with robots or other embodied systems (such as autonomous vehicles) is strongly preferred, particularly in the manipulation domain. If our mission of revolutionizing robotics through machine learning resonates with you, then let’s talk about how we can create the next generation of AI-powered capable robots together.

Requirements

4+ years of relevant industry experience or a PhD.
Experience training large models and deploying them on embodied systems.
Strong software development skills in Python, familiarity with mixed C++/Python codebases, and a focus on clean, maintainable code.
Extensive experience with Machine Learning using a major framework such as PyTorch or TensorFlow.
Familiarity with data pipelines, model serving and optimization, cloud training, and dataset management.
Strong understanding of the state-of-the-art in robot learning, including vision-language-action (VLA) models, reinforcement learning, and/or computer vision.
Practical experience with robots and the system integration challenges inherent in conducting research and deploying onto physical hardware platforms.
An ability to adapt quickly and switch between modes of rapid prototyping and robust implementation as required.
A consistent track record of impact, either via first author research publications at top-tier machine learning or robotics conferences (RSS, NeuRIPS, ICML, ICLR, CoRL, ICRA, IROS, …), or via relevant contributions to successful industry initiatives.

Nice To Haves

Experience with robotic middleware such as ROS 2 and common communication methods and protocols.
Experience with modern ML infrastructure pipelines, approaches, and tools.
Experience with VR-based teleoperation for real-time robot control.
Background or familiarity with some of the following: motion control and actuation, whole-body control, reinforcement learning, robot teleoperation methods, common communication protocols, research robotic arms/systems, visual perception and depth sensors, machine learning, robotic simulation, force and tactile sensing systems, haptic interfaces.

Responsibilities

Work as part of a dynamic, closely-knit research team building useful robots and general-purpose robot foundation models.
Implement, extend, and create innovative methods for robot behavior learning from a mixture of interactive embodied data and online data sources.
Design and implement high-performance machine-learning pipelines and optimize data and learning stacks for scalability, efficiency, and performance.
Be a key member of the team and play a critical role in rapid progress measured by both the development of internal capabilities and high-impact external publication.
Collaborate with internal research scientists and our partner labs at top academic research universities including MIT, Stanford, Berkeley, CMU, Columbia, and Princeton to drive pioneering research at scale.

Benefits

TRI offers a generous benefits package including medical, dental, and vision insurance, 401(k) eligibility, paid time off benefits (including vacation, sick time, and parental leave), and an annual cash bonus structure.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume