Mountain View, CA (On-Site) · Full-time Mountain View, CA (On-Site)

Robotics Engineer/Researcher - Data Engine & Deployment - Teleoperation Systems, Data Pipelines, On-Robot Systems

Join our team to build the data engine behind general-purpose robot policies. You'll own the pipeline from teleoperated demonstration collection through curation and quality control to on-robot deployment — the systems that turn robot time into training data, and trained policies into robots that work in the real world. We care more about your ability to build reliable, high-throughput systems around real robots than about any particular robot, task, or sensor you've used before.

Requirements

• 01 BS, MS, or PhD in Robotics, Computer Science, Electrical Engineering, or related field — or equivalent experience
• 02 Strong software engineering skills in Python and C++ in Linux environments: you write robust, maintainable systems code that runs on real hardware
• 03 Hands-on robotics experience: hardware bring-up, sensor and actuator integration, calibration, and debugging full-stack issues on physical systems
• 04 Experience building teleoperation and demonstration-collection systems — rigs, operator interfaces, and workflows — and scaling collection throughput and operator efficiency
• 05 Experience building data pipelines for multimodal robot data: ingestion, time synchronization across sensors, storage and dataset formats, curation, filtering, and annotation tooling
• 06 Experience deploying learned policies on real robots: real-time inference, latency and throughput optimization, safety monitors, and graceful failure handling
• 07 Comfortable working with multimodal sensor streams (RGB/depth cameras, proprioception, tactile, force-torque) — drivers, logging, and synchronized capture
• 08 Rigorous about data quality: metrics and visualization for dataset coverage and consistency, automated QA, and regression testing of the collection-to-deployment loop
• 09 (+) Experience with ROS 2 or comparable robotics middleware, real-time systems, and containerized deployment across a fleet of robots
• 10 (+) Familiarity with robot learning workflows (imitation learning, vision-language-action models) — enough to shape data collection around what models actually need
• 11 (+) Experience with dexterous hands, tactile sensing, or contact-rich manipulation setups

Details & responsibilities

• 01 Design and build the teleoperation and demonstration-collection stack — rigs, operator interfaces, and workflows that maximize throughput and data quality
• 02 Run data collection operations end to end: task and protocol design, operator onboarding, and day-to-day collection on real robots
• 03 Build the pipeline from robot to training set: ingestion, time synchronization of multimodal sensor streams, storage and dataset formats, curation, filtering, and annotation tooling
• 04 Develop the QA, metrics, and visualization tooling that keeps datasets consistent, well-covered, and trustworthy
• 05 Deploy trained policies to real hardware: real-time inference, latency optimization, safety monitors, and graceful failure handling
• 06 Bring up and integrate sensors and hardware — cameras, tactile, force-torque — across collection and deployment rigs
• 07 Collaborate across AI, hardware, and perception teams to close the loop from deployment results back into data collectio
• 01 Competitive salary and meaningful equity
• 02 Full health, dental, and vision insurance
• 03 Access to custom-built dexterous robots
• 04 Collaboration with leading researchers in robotics and AI
• 05 Backed by YC and top-tier investors
• 06 High-ownership role with the opportunity to lead core initiatives in real-world robot learning