Mecka.Ai
Online Calibration & SLAM Engineer
Toronto GTA, Remote. Posted a month ago
The role
You will own online calibration systems to detect and correct camera and IMU drift across a device fleet. You will build monitoring tools, maintain SLAM/VIO foundations, and coordinate with hardware teams.
What you will do
- Develop and maintain continuous, in-pipeline camera calibration.
- Fix and harden the video-based calibration refinement system.
- Build monitoring and metrics tracking to detect calibration drift.
- Own the calibration database and version history.
- Maintain and improve the SLAM/VIO that online calibration rides on.
- Coordinate with the factory-calibration engineer and China hardware team.
- Ship interactive tools to visualize trajectories, drift, and metrics.
Required qualifications
- 5+ years of hands-on experience building, maintaining, or improving SLAM, visual-inertial odometry, and Structure-from-Motion pipelines, including systems running in production.
- Hands-on experience with online or continuous calibration and rigorous camera + IMU calibration: extrinsics, intrinsics and their limits, IMU noise density and random-walk bias, lens-distortion models
- Comfortable owning calibration across many noisy, real-world devices.
- Intuitive grasp of the linear algebra, optimization, and first principles behind spatial tracking.
- Clean, efficient, scalable C++ and Python.
- Ability to specify calibration requirements clearly to a hardware team across time zones.
Nice to have
- Experience with video-based or markerless calibration and refinement systems.
- Sensor-fusion and calibration tools such as Kalibr, GTSAM, or Ceres Solver.
- OpenCV, COLMAP, PyTorch, and FFmpeg.
- Monitoring at scale, including calibration databases and versioning.
- Rerun, Gradio dashboards, or trajectory and dataset browsers.
- ML infrastructure or data pipelines that operate at scale.
About the company
Mecka AI is building the data infrastructure layer for robotics and embodied AI. They design and operate global systems for data capture, data labeling, and hardware-enabled workflows.