Applied Researcher - Dexterous Manipulation
Vancouver, BC
AI/Machine Learning – AI/Automation /
Full-Time /
Hybrid
Your New Role and Team
Sanctuary, a world leader in building AI-based control systems for humanoid robots, is seeking an exceptional Applied Researcher to join our team in engineering and innovating unique robotic manipulation tasks.
As an Applied Researcher, you'll be responsible for selecting the most promising state of the art (SOTA) approaches, designing training and data-collection pipelines, supervising the process of testing these algorithms in simulation, and deploying them to our robots in real-world settings. With access to in-house robots with dexterous hands, you'll also have a unique opportunity for impactful work with new haptic and proprioceptive sensing modalities.
Success Criteria
- 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 SOTA RL/IL methodologies and robotics
- Identify, communicate, and drive promising research directions to the team
- Find ways of improving existing implementations of RL/IL learning 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
- PhD in Machine Learning, Computer Science, Applied Math, or equivalent work experience in ML
- 3+ years' experience implementing and deploying (dexterous) robotic manipulation tasks in simulation and on physical robots
- Proven expertise in sim-to-real transfer
- Experience taking ML R&D and trained models into production
- Hands-on experience integrating ML models onto a robotics platform
- Experience with computer vision systems
- Publications in leading AI conferences such as ICRA, IROS and CORL
- Extensive knowledge of Reinforcement Learning and Imitation Learning principles and use
- Development with Python 3.8 or later
- Working knowledge of PyTorch and/or TensorFlow
- Familiarity with ROS2
- Experience with Atlassian tools; Jira, Confluence, or equivalent i.e. GitLab
- Above all else, a consistently positive attitude and a willingness to do whatever it takes to create robust solutions to complex problems
- Strong leadership skills in organizing R&D work for ML projects
- Eager to take on new challenges with tenacity and positivity
- Patience, persistence, and attention to detail when resolving performance issues
- Enthusiasm for bringing human-like intelligence to machines
- Ability to drive development of new functionalities from concept to production
- Ability to multitask and prioritize in a fast paced environment
Your Experience
Qualifications
Skills
Traits
Working at Sanctuary AI
Sanctuary AI is an equal opportunity employer; employment with Sanctuary AI is governed based on skills, competence, and qualifications and will not be influenced in any way by race, color, religion, gender, national origin/ethnicity, veteran status, disability status, age, sexual orientation, gender identity, marital status, mental or physical disability, or any other legally protected status. In 2023, Sanctuary AI moved into a state-of-the-art office facility and has been recognized by LinkedIn as a Top Startup company.
Compensation and 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.
About Sanctuary AI
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.
Recruiting and Employment Agency Notice:
Recruitment and hiring is conducted internally by Sanctuary AI. We are not seeking or soliciting any new agency partnerships or agreements at this time. Any employment agency or professional recruiter (“Agency”) that provides an unsolicited resume(s) or otherwise presents a prospective job candidate through the Sanctuary AI career site or directly to any Sanctuary AI employee, irrevocably grants to Sanctuary AI the unrestricted right to engage, hire, or contract with that candidate at Sanctuary AI's sole discretion without any compensation to the Agency. We appreciate your interest in working together, and should the need arise our Talent Acquisition team will contact any external firms directly.