Perception & Localization · Internship

VSLAM & Ego Data Intern

Responsibilities

Develop multi-camera and IMU acquisition and synchronization, including timestamps, transport, buffers, and quality monitoring.
Help build camera–IMU calibration tools covering intrinsics, extrinsics, time offset, and rolling-shutter parameters.
Implement and debug feature tracking, IMU preintegration, nonlinear optimization, loop closure, and relocalization for VIO/VSLAM.
Deploy on Ego or embedded Linux devices and evaluate compute, latency, memory, real-time performance, and stability.
Analyze dropped frames, time drift, calibration/exposure issues, IMU noise, and broken trajectories.

Currently pursuing a master’s or PhD in computer vision, robotics, automation, surveying, electronic information, computer science, or AI.
Familiar with C++ or Python and Linux, with sound algorithm and system debugging skills.
Understand camera, fisheye/wide-angle, and IMU models, coordinate transforms, synchronization, and calibration.
Understand VSLAM/VIO: feature extraction/tracking, IMU preintegration, PnP, BA, nonlinear optimization, sliding windows, and loop closure.
Hands-on ability to integrate sensors, capture data, debug algorithms, and analyze real-hardware results.

Experience with Jetson, ARM, Android, embedded Linux, GPU/NPU acceleration, or real-time systems.
Familiarity with ORB-SLAM3, VINS-Fusion, OpenVINS, OKVIS, Kimera, Kalibr, or OpenCalib.
Experience with PTP, GMSL, MIPI, USB cameras, high-bandwidth transport, IMU drivers, or sensor boards.
Experience with acquisition systems, automated calibration, sensor diagnostics, or trajectory quality tools.
Relevant publications at ICRA, IROS, RSS, CVPR, ICCV, ECCV, or CoRL.

Synchronization, calibration, localization, and quality systems for Ego devices.
The complete workflow from sensor integration and calibration to VSLAM/VIO and edge deployment.
The intersection of multi-camera sensing, IMUs, visual-inertial localization, and robotics data infrastructure.