Apply now »

Senior Computer Vision Engineer

Business Unit:  Chief Innovation Office
Division:  Core R&D
Department:  Core R&D Lab

Your Mission

This position is responsible for designing, implementing, and optimizing computer vision algorithms that are integral to our robotic systems. The successful candidate will take charge of designing and developing robust 2D and 3D computer vision algorithms for object detection, recognition, and tracking as well as for visual SLAM, human activity recognition, and 3D reconstruction applications.

What To Expect

  • Process 2D image and 3D pointcloud data to develop vision and perception algorithms for various robotic systems.
  • Integrate Superpoint or similar feature detectors for robust visual SLAM functionalities.
  • Design and implement advanced computer vision algorithms for 3D reconstruction and scene understanding.
  • Perform sensor calibration for multiple cameras and LiDAR systems to ensure accurate perception data.
  • Understand and develop deep learning AI models for object segmentation and human activity recognition.
  • Evaluate and validate the performance of the implemented algorithms on real-world datasets. 
  • Documentation of technical reports, program codes, and set-up manuals.

What You'll Bring

  • A Master's or Ph.D. degree in Electrical/Mechanical/Computer Engineering or relevant discipline with more than 5 years of industry experience.
  • Solid foundation in computer vision, multiple view geometry, and deep learning techniques for both 2D and 3D data.
  • Strong understanding of camera sensor principles (e.g, image formation, noise characteristics, and resolution limitations).
  • Ability to evaluate and shortlist candidate solutions or sensors based on technical feasibility, performance, and cost.
  • Proven experience in developing and deploying computer vision algorithms in real-world applications.
  • Familiarity with object detection, recognition and segmentation AI frameworks (e.g., YOLO, Faster R-CNN, Mask2former).
  • Strong experience with point cloud registration algorithms (e.g., ICP, GMM) and relevant libraries (e.g., Open3D, PCL).
  • Experience with human detection and human activity recognition models (e.g., I3D, C3D).
  • Understanding of interest point detection and description (e.g., SuperPoint, LIFT, D2-Net).
  • Expertise in programming languages such as C/C++ and Python. 
  • Familiarity with computer vision libraries (e.g., OpenCV) and machine learning frameworks (e.g., TensorFlow, PyTorch).
  • Any patent, publication, specialist certification, or award in robotics and automation is an added advantage.

Before submitting your job application, please review our Data Protection Policy

Apply now »