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

• (+) Experience with dexterous hands, tactile sensing, or contact-rich manipulation setups

• Competitive salary and meaningful equity

• Full health, dental, and vision insurance

• Access to custom-built dexterous robots

• Collaboration with leading researchers in robotics and AI

• Backed by YC and top-tier investors

• High-ownership role with the opportunity to lead core initiatives in real-world robot learning

• Design and build the teleoperation and demonstration-collection stack — rigs, operator interfaces, and workflows that maximize throughput and data quality

• Run data collection operations end to end: task and protocol design, operator onboarding, and day-to-day collection on real robots

• Build the pipeline from robot to training set: ingestion, time synchronization of multimodal sensor streams, storage and dataset formats, curation, filtering, and annotation tooling

• Develop the QA, metrics, and visualization tooling that keeps datasets consistent, well-covered, and trustworthy

• Deploy trained policies to real hardware: real-time inference, latency optimization, safety monitors, and graceful failure handling

• Bring up and integrate sensors and hardware — cameras, tactile, force-torque — across collection and deployment rigs

• Collaborate across AI, hardware, and perception teams to close the loop from deployment results back into data collectio