Staff Software Engineer, Teleoperation

Your New Role and Team

Sanctuary AI is hiring a Staff Software Engineer to drive and evolve the production teleoperation and data collection software that enables robot operators to control robots.

You will combine strong engineering execution with research capability: evaluating new approaches and bringing them into production. As a hands-on technical leader, you will guide architecture decisions, mentor engineers and translate company priorities into practical technical plans.

Our Success Criteria

• Deliver reliable production software, taking features from prototype through testing, integration, deployment and operational support

• Generate accurate, low-latency robot targets from motion capture and other operator inputs, visual and haptic feedback, including force feedback performance and comfort

• Improve the reliability and quality of demonstration Improve the reliability and quality of demonstration collection through software improvements and new collection methods

• Evaluate relevant research and new control, feedback or collection methods through experiments, and turn promising results into maintainable, production-ready features

• Guide architecture and technical priorities in alignment with the broader product roadmap, coordinating implementation with controls, hardware, ML and Customer Solutions

• Mentor engineers through code and design reviews, architectural guidance, and evaluation of relevant research

Your Experience

• A track record of shipping and supporting production robotics software, with strong C++ and Python skills and experience using Linux (preferably Debian or Ubuntu), Git and CI/CD

• Strong software architecture judgment and practical experience integrating and debugging latency-sensitive robotic systems, including hardware-in-the-loop testing

• Working knowledge of ROS 2 and robotics software interfaces

• Understanding of coordinate-frame transforms and forward and inverse kinematics

• Practical teleoperation experience or closely transferable robotics experience, with knowledge of current approaches and how demonstration collection supports physical AI

• Demonstrated research experience in robotic data collection, teleoperation or related operator-interface technologies, with evidence of translating findings into working systems

• Experience mentoring engineers and driving technical decisions across software, controls, hardware and ML or automation teams. You can explain and defend a position while responding to new evidence

• A master's or Ph.D. in Robotics, Computer Science, Electrical Engineering, Mechanical Engineering or a related field, or equivalent industry experience

Additional Experience We Value

• Robotics data acquisition, demonstration quality assessment or policy-training workflows

• Experience with TF2, URDF/SRDF, DDS or ros2_control

• Cameras and video pipelines, operator interfaces, motion capture, VR or haptic feedback

• Dynamics, signal processing, impedance or admittance control, numerical optimization, optimal control or ML for control

What You Will Learn at Sanctuary

You will learn our robot architecture and interfaces, hand-mapping and kinematic-retargeting approaches, OpenXR and motion-capture systems, and how our data collection and policy-training pipelines support robots performing real-world tasks.

Working at Sanctuary

Sanctuary AI is an equal opportunity employer. Employment with Sanctuary AI is governed by skills, competence and qualifications and will not be influenced by any legally protected status.

Compensation and Benefits

Sanctuary AI offers a market-leading compensation package that includes competitive salaries, equity stakes and a full suite of benefits for permanent employees, including health coverage, paid time off, cutting-edge work facilities and worksite flexibility by role.

About Sanctuary

Founded in 2018, Sanctuary AI builds robots and a novel control system 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.