Staff Research Scientist - Mobile Manipulation, Perception

Key Skills

AI Robotic systems, Algorithms, C++, Deep Learning, Large data sets, Python Programming

Job Description

The team is passionate about heavily using machine learning to marry perception, prediction, and action to produce robust, reactive, and coordinated robot behaviors, bootstrapping from simulation and synthetic data, using large amounts of data, and adapting in real-world scenarios.

TRI has the runway, roadmap, and expertise to transition the technology development to a product that impacts the lives of millions of people. Apply to join a fast-paced team that demands high-risk innovation and learning from failures, using thorough processes to identify key technologies, develop a robust, high-quality system, and quantitatively evaluate performance. As part of the team, you will be surrounded and supported by the significant core ML, cloud, software, and hardware expertise at TRI, and be a part of TRI's positive and diverse culture.

Responsibilities

• Develop, integrate, and deploy algorithms linking perception to autonomous robot actions, including manipulation, navigation, and human-robot interaction.
• Invent and deploy innovative solutions at the intersection of machine learning, computer vision, multi-sensor perception, and simulation for understanding human environments and humans, in and around homes.
• Invent novel ways to generate, build, label, and use large, possibly distributed datasets, using self-supervision, active learning, simulation, synthetic rendering, and real-world adaptation.
• Be part of a team that fields systems, performs failure analysis, and iterates on improving performance and capabilities.
• Follow software engineering practices that produce maintainable code, including automated testing, continuous integration, code style conformity, and code review.

Qualifications

• S. or Ph.D. in an engineering-related field.
• A strong background in inventing and deploying innovative perception algorithms to robotic systems in real-world environments.
• Experience in areas such as object detection, classification, segmentation, and tracking, sensor fusion, state estimation, local 3D mapping and reconstruction, person detection, and human pose estimation.
• Experience in developing and training deep nets and applying deep learning to perception problems.
• Strong software engineering skills, preferably in both Python and C++, and analysis and debugging of robotic perception algorithms.
• Strong interpersonal skills, and a willingness to learn from others and contribute back to the robotics community with publications or open-source code.
• Passionate about seeing robotics have an impact.

The pay range for this position at commencement of employment is expected to be between $220,800 and $317,400/year for California-based roles; however, base pay offered may vary depending on multiple individualized factors, including market location, job-related knowledge, skills, and experience. Note that TRI offers a generous benefits package (including 401(k) eligibility and various paid time off benefits, such as vacation, sick time, and parental leave) and an annual cash bonus structure. Details of participation in these benefit plans will be provided if an employee receives an offer of employment.

Please reference this Candidate Privacy Notice to 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.