The next ten years of AI will not be won in software. They will be won in the physical world. In factories, hospitals, kitchens, fields, and homes. The companies that own that data will own the century.

microagi is building it. We are the data layer for physical AI.

You will own the SLAM stage. From egocentric footage and IMU, you produce the camera trajectory and a 3D map of the space the person moved through. Everything downstream sits on top of it. If the trajectory drifts, the annotations built on it are wrong and nobody finds out until the customer does.

What You Will Do

• Own visual-inertial SLAM end to end, from raw capture to trajectory and map.
• Produce accurate 6-DoF trajectories and 3D reconstructions from head-mounted cameras.
• Handle the cases that break SLAM. Fast head motion, blank walls, people crossing the scene, long occlusions.
• Own camera and IMU calibration, including intrinsics, extrinsics, and time synchronization across sensors.
• Build evaluation against ground truth and track accuracy as the hardware changes underneath you.
• Make it run at the throughput the pipeline needs, not just on your laptop.

Requirements

• Production or research experience with visual-inertial SLAM, VIO, or structure from motion.
• Strong state estimation. Factor graphs, bundle adjustment, filtering.
• Strong C++ and Python.
• Experience calibrating and time-synchronizing sensors on real hardware.
• You have chased down a trajectory that drifted and found out why.
• High agency - you don't wait to be told what to do.
• Fluent in English.

Nice to Have

• Experience with ORB-SLAM, COLMAP, GTSAM, Kalibr, or similar.
• Dense reconstruction, TSDF fusion, or Gaussian splatting.
• Work with head-mounted or wearable capture rigs.

#LI-DNI