Senior Research Engineer

Senior Research Engineer, Computer Vision

You will advance computer vision algorithms for semantic scene segmentation, motion tracking, image modeling, image registration, and 3D model reconstruction to promote integration of CG, CV, AI and image processing technologies into a unified pipeline to provide a tool chain for better digital reality experience.

Develop vision-based indoor and outdoor positioning systems that process multi-modal information from multiple sensors, design visual location recognition systems that are robust to variations in the capture conditions and viewpoint changes.

Implement optimized and accurate solutions for on-device that use reduced memory and run in real-time.

Work with multiple 3rd Party SDKs to integrate computer vision algorithms, AR/VR tracking, and haptics applications to build experimental prototypes.

Qualifications

• PhD or MS in Computer Science, Electrical Engineering or a related field
• At least three-year experience in computer vision
• Essential hands-on experience in developing computer vision solutions involving:
• State-of-the-art intensity and feature based image/video registration and alignment algorithms for camera calibration, photogrammetry, depth estimation and structure from motion
• Reconstruction and updating a map of the environment while simultaneously keeping track of sensor location (SLAM), georeferencing and positioning
• Clustering parts of images together which belong to the same object class
• Solid understanding and extensive experience with object detection and recognition based on deep learning:
• Involving ResNet, DenseNet, MobileNet, YOLO, VGG, etc.
• Preferably implemented with TensorFlow library
• Well versed in the state-of-the-art in real time 2D and 3D data processing, feature design, training, cross-validation, feature down-selection, performance evaluation
• Experience in technologies for AR/VR, haptics, 3D graphics including rendering and simulation
• Experience in working with data from RGB cameras, IR cameras, depth cameras
• Experience operating on large datasets, data collection, data labeling
• Very strong implementation skills in C++, Python using OpenCV
• Research publications at good venues are a plus
• Highly motivated to work as a team player and as an individual contributor
• Comfortable working in a fast-paced environment, and a can-do attitude
• Good oral and written communication, interpersonal skills and fluency in English.