About the Role
- Sanctuary AI, a world leader in building dexterity-driven Physical AI for general purpose robots, is looking to hire a skilled and motivated intern to join our ML team and contribute to our team’s work in engineering and innovating unique robotic manipulation tasks. Reporting to the RL Lead, you will have the opportunity to tackle a variety of challenges related to the perception, planning, and motion systems for humanoid general-purpose robots. The best candidates for this role have excellent software development and machine learning skills as well as hands-on experience with robotics. In this role you’ll be a valued contributor and you’ll gain a comprehensive understanding of the design, architecture, and implementation of the simulation platform and machine learning systems that power our general-purpose robots. We are flexible regarding both the internship start date and the duration of the term.
- Founded in 2018, Sanctuary builds humanoid robots and a novel control system for them that integrates symbolic logic and reasoning with data-driven robot foundation models. We use our robots to collect vision, audio, touch, and proprioception data from the perspective of the robot while they perform real-world work tasks. We use that data to train multimodal robot foundation models. Because our systems are vertically integrated, we can design, deploy, and refine at scale. Our mission is to create the world's first human-like intelligence in general-purpose robots.
Responsibilities
- Design, implement, and improve state-of-the-art Reinforcement Learning (RL) and Imitation Learning (IL) algorithms and test them in real-world settings
- Keep up to date with state-of-the-art RL/IL methodologies and robotics
- Identify, communicate, and drive promising research directions to the team
- Find ways of improving existing implementations of RL/IL pipelines with regards to standard metrics such as sample efficiency, speed, computational resource usage, and scalability
- Design RL/IL training and data-collection pipelines to facilitate fast deployment on physical robots
- Work with a multidisciplinary team to develop novel algorithms and investigate sources of errors with existing implementations
Requirements
- Pursuing MS or Ph.D. in Machine Learning, Computer Science, Applied Math, or related field
- Experience implementing a variety of RL and IL methods with a focus in a specialization such as computer vision or robotics
- Hands-on experience integrating ML models onto a robotics platform
- Experience implementing and deploying (dexterous) robotic manipulation tasks in simulation and on physical robots
- Experience taking ML R&D and trained models into production
- Development with Python 3.6 or later
- Working knowledge of PyTorch and/or JAX
- Extensive knowledge of RL/IL principles and use
Qualifications
- Experience with computer vision systems
- Experience in simulation-to-reality transfer learning
- Familiarity with ROS2
Benefits
Sanctuary offers a market-leading compensation package that includes competitive salaries, equity stakes, and a full suite of benefits for permanent employees, encompassing health coverage, paid time off, cutting-edge work facilities, and worksite flexibility by role. Our commitment to fairness ensures that our total compensation consistently surpasses market standards.