Research Scientist, Trustworthy Learning under Uncertainty (TLU) Large Behavior Models

Los Altos, CA - USA

Yearly Salary: $ 176000 - 264000

Posted on: 30+ days ago

Vacancies: 1 Vacancy

The job posting is outdated and position may be filled

Job Summary

At Toyota Research Institute (TRI) were on a mission to improve the quality of human life. Were developing new tools and capabilities to amplify the human experience. To lead this transformative shift in mobility weve built a world-class team advancing the state of the art in AI robotics driving and material sciences.

The Mission

To conduct cutting-edge research that will enable general-purpose robots to be reliably deployed at scale in human environments.

The Challenge

We envision a future where robots assist with household chores and cooking aid the elderly 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 reliably in messy unstructured environments.

Recent years have witnessed a surge in the use of foundation models in various application domains particularly in robotics. These large behavior models (LBMs) are enhancing the abilities of autonomous robots to perform various complex tasks in open and interactive environments. TRI Robotics is at the forefront of this emerging field by applying insights from foundation models including large-scale pre-training and generative deep learning. However it remains a challenge to ensure the reliability of LBMs for large-scale deployment in diverse operating conditions.

The Team

We aim to make progress on some of the hardest scientific challenges around the safe and effective usage and development of machine learning algorithms within robotics. To this end the research mission of the Trustworthy Learning under Uncertainty (TLU) team within the Robotics division is to enable the robust reliable and adaptive deployment of LBMs at scale in human environments.

To guarantee dependable deployment at scale in the years to come we are dedicated to enhancing trustworthiness of LBMs through three key principles as detailed (i) ensuring objective assessment of policy performance (Rigorous Evaluation) (ii) improving the ability to detect and handle unknown situations and return to nominal performance (Failure Detection and Mitigation) and (iii) developing the capability to identify and adapt to new information (Active / Continual Learning).

Our team has deep cross-functional expertise across controls uncertainty-aware ML statistics and robotics. We measure our success in terms of algorithmic advancements in the state-of-the-art and publications of these results in high-impact journals and conferences. We value contributions of reproducible and usable open-source software.

The Opportunity

Were looking for a driven research scientist or research engineer with a strong background in embodied machine learning and a make it happen mentality. Specifically we are looking for expertise in a variety of areas such as Policy Evaluation Failure Detection and Mitigation and Active Learning in the context of Large Behavior Models (LBMs) for robotic manipulation. Our topics of interest include but are not limited to: Multi-Modal Foundation Models Generative Modeling Imitation Learning Reinforcement Learning Planning & Control Statistics Uncertainty Estimation Out-of-Distribution Detection Safety-Aware & Robust ML (Inter)Active Learning and Online / Continual Learning.

The ideal candidate is able to conduct research independently but also works well as part of a larger research team at the cutting edge of state-of-the-art robotics and machine learning. Experience with robots is preferred particularly in the manipulation domain.

If our mission of robust reliable and adaptive deployment of LBMs at scale in human environments resonates with you reach out by submitting an application!

Responsibilities

Work as part of a dynamic closely-knit team conducting research on reliable robust and adaptive deployment of machine learning models in robot manipulation.
Push the boundaries of knowledge and the state-of-the-art in Robotics and LBMs.
Contribute to cutting-edge development in the areas of: Rigorous Policy Evaluation Failure Detection and Mitigation and Active / Continual Learning.
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 engineers across the TLU team Robotics division TRI and Toyota as well as our university partners across top academic research universities such as MIT Stanford CMU Columbia USC and Princeton.
Present results in verbal and written communications at international conferences internally and via open-source contributions to the community.

Qualifications

4 years of relevant industry experience or a Ph.D. in Machine Learning Robotics or related fields.
Passionate about large scale challenges in ML grounded in physical systems especially in the space of robotic manipulation.
Expertise in Multi-Modal Foundation Models Generative Modeling Imitation Learning Reinforcement Learning Planning & Control Statistics Uncertainty Estimation Out-of-Distribution Detection Safety-Aware & Robust ML (Inter)Active Learning and/or Online / Continual Learning.
A strong track record of publication at high-impact conferences/journals (e.g. CoRL ICLR NeurIPS ICML UAI AISTATS AAAI TMLR RSS ICRA IROS RA-L T-RO CDC L4DC etc.) on some of the aforementioned topics.
Proficiency with one or more coding languages and systems preferably Python Unix and a Deep Learning framework (e.g. PyTorch).
Ability to collaborate with other researchers and engineers of the TLU team and more broadly the Robotics division to invent and develop interesting research ideas.
A reliable teammate who loves to think big go deeper and deliver with integrity.

Bonus Qualifications

Some familiarity with robots and the challenges inherent in conducting research on physical hardware platform.
Familiarity with data pipelines model serving and optimization cloud training and dataset management is also useful.

The pay range for this position at commencement of employment is expected to be between $176000 and $264000/year for California-based roles. Base pay offered will depend on multiple individualized factors including but not limited to business or organizational needs market location job-related knowledge skills and experience. 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. Additional details regarding these benefit plans will be provided if an employee receives an offer of employment.

Please reference thisCandidate Privacy Noticeto inform you of the categories of personal information that we collect from individuals who inquire about and/or apply to work for Toyota Research Institute Inc. or its subsidiaries including Toyota A.I. Ventures GP L.P. and the purposes for which we use such personal information.

TRI is fueled by a diverse and inclusive community of people with unique backgrounds education and life experiences. We are dedicated to fostering an innovative and collaborative environment by living the values that are an essential part of our culture. We believe diversity makes us stronger and are proud to provide Equal Employment Opportunity for all without regard to an applicants race color creed gender gender identity or expression sexual orientation national origin age physical or mental disability medical condition religion marital status genetic information veteran status or any other status protected under federal state or local laws.

It is unlawful in Massachusetts to require or administer a lie detector test as a condition of employment or continued employment. An employer who violates this law shall be subject to criminal penalties and civil liability. Pursuant to the San Francisco Fair Chance Ordinance we will consider qualified applicants with arrest and conviction records for employment.

We may use artificial intelligence (AI) tools to support parts of the hiring process such as reviewing applications analyzing resumes or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed please contact us.

Required Experience: