Sensor Calibration Engineer

At Mentee Robotics, we are redefining humanoid automation with an AI-first approach - combining perception, reasoning, and dexterous manipulation into fully autonomous systems that continuously learn and improve. We offer an exceptional opportunity to participate in building next-generation commercial humanoid robots from 0 to 1, alongside competitive compensation, and an international engineering environment. We are expanding with a new robotics Engineering Center in China, working hand-in-hand with our engineering teams in headquarters. Its mission: to rapidly develop our next-generation full-size humanoid platform and bring it to production.

We are looking for a Sensor Calibration Engineer to own intrinsic and extrinsic calibration algorithms, online self-recalibration routines, software calibration pipelines, and spatial-temporal alignment for our humanoid robot’s multi-modal sensor suite (cameras, LiDAR, IMU, kinematics, and force-torque sensors).

 

Who you are:

Calibration specialist deeply versed in 3D geometry, spatial transformations, state estimation, non-linear optimization, and sensor error modeling.

Hands-on engineer who excels at mathematical model formulation, algorithmic solver design, and numerical optimization.

Driven to translate complex calibration formulations into automated software routines and online self-correcting algorithms.

A strong collaborator across computer vision, SLAM, state estimation, control, and production quality teams.

Responsibilities:

Design and implement intrinsic and extrinsic calibration algorithms for multi-camera systems, LiDAR, IMU, joint encoders, and force/torque sensors.

Develop joint spatial-temporal calibration pipelines to accurately estimate inter-sensor rotation/translation matrices and temporal offsets.

Architect automated calibration software pipelines and trajectory generation algorithms to support scalable sensor calibration workflows.

Implement online self-calibration and drift-tracking algorithms to maintain cross-sensor spatial alignment during continuous dynamic motion.

Integrate kinematic-visual-inertial calibration algorithms to model structural compliance, thermal expansion, and gravity deflection.

Deliver calibrated transformations (TF trees, extrinsic matrices, distortion parameters) directly into perception, localization, and control stacks.

Conduct residual error sensitivity analysis, repeatability validation, and environmental robustness testing across thermal cycles and dynamic vibration.

Requirements:

B.Sc. or M.Sc. in Computer Science, Robotics, or related technical disciplines.

3+ years of hands-on experience in multi-sensor calibration, computer vision geometry, spatial optimization, or SLAM/state estimation.

Solid mathematical foundation in 3D rigid-body transformations, Lie algebra (SE(3), SO(3)), non-linear optimization (Ceres, g2o), and Kalman filtering.

Proficient in Modern C++ and Python, with experience utilizing OpenCV, PCL, and ROS 2 coordinate transformation tools (TF2).

Practical experience in camera intrinsic/extrinsic calibration, camera-LiDAR calibration, and camera-IMU spatiotemporal calibration (e.g., Kalibr).

Experience developing automated calibration software workflows and verification tools.

Strong analytical problem-solving skills and rigorous data-driven evaluation methodologies.

Advantages:

Direct experience in humanoid or quadruped kinematic-visual-inertial self-calibration routines.

Knowledge of thermal error modeling for IMU gyroscopes/accelerometers and optical sensor distortion.

Comfortable communicating technical topics in English with international teams.