Founding Robotics Perception Engineer | YC-Backed Physical AI & Robotics Startup | London (Remote) | Full-Time | Up to £150K + Equity

About the Company

Our client is a Y Combinator-backed (S26) physical AI data company building the foundational human video and motion datasets for leading robotics and embodied-AI teams. Focused on egocentric first-person video and UMI demonstration data, the company turns real-world capture operations into high-precision, versioned data products that foundation-model and VLA teams rely on to train physical robots.

Backed by a freshly closed seed round, their core constraint is supply, not demand. They are actively scaling deployment engineering, field operations, and capture hardware to keep up with massive customer demand.

The founders are building a three-person founding engineering team to set the technical standards, tooling, and evaluation methodology behind the world's reference dataset for robot learning.

About the Role

Reporting to the Engineering Lead (with direct collaboration with the Founders), the Founding Robotics Perception Engineer owns hand tracking, motion reconstruction, and capture-device software integration. You will serve as the technical authority on turning raw camera and sensor recordings into accurate, physical 3D trajectories.

Your work directly determines whether the motion data is accurate enough for its intended use and sets the company's technical standard for motion data. You will build production pipelines for 3D hand tracking and gripper trajectory estimation, integrate camera SDKs and spatial sensors, and establish the physical accuracy benchmarks and quality flags that give robotics teams total confidence in the data.

Key Responsibilities

• Build, refine, and maintain production pipelines for 3D hand tracking from egocentric video and gripper trajectory reconstruction from UMI recordings.

• Integrate camera streams, IMUs, and device SDKs into the collection software, ensuring flawless handling of spatial calibration, coordinate frames, timestamps, and units.

• Develop diagnostic tools to detect occluded hands, lost tracks, motion drift, coordinate discrepancies, dropped frames, and timestamp misalignments, applying automated quality flags for data review.

• Compare motion estimates against physical reference standards, quantify error and coverage, and maintain automated regression tests to confirm that pipeline changes genuinely improve data accuracy.

• Test and benchmark newly purchased cameras and capture hardware on representative tasks, evaluating baseline signal quality and reliability prior to wider operational deployment.
  
  

Skills & Competencies

• Deep spatial understanding of 3D camera geometry, camera-IMU calibration, coordinate transforms, temporal tracking, and multi-view reconstruction.

• Hands-on experience with 3D hand tracking, visual odometry, SLAM, or pose estimation using real-world camera and sensor recordings.

• Strong production programming capabilities in Python (along with C++ and GPU inference where required) backed by practical deep learning implementation skills.

• Exceptional ability to separate model errors from sensor faults, isolating physical discrepancies, dropped frames, and timestamp drift.

Qualifications & Experience

• Background in hand tracking, motion capture, AR/VR, spatial computing, robotics, autonomous systems, or sensor fusion.

• Proven track record of taking perception or tracking systems beyond controlled lab conditions to real sensor recordings used by actual applications.

• Direct experience handling raw device SDKs, coordinate frame conventions, and physical accuracy validation against meaningful ground-truth references.

• Experience with egocentric video, camera-IMU setups, visual odometry, or multi-view reconstruction is highly valuable.
  
  

Role Details

• Timing: Immediate Start

• Location: London (Remote).

• Package: Competitive base salary up to £150K + significant founding-engineer equity with total technical ownership over the perception domain.