Computer Vision Research Engineer - Apple Maps 3D Vision Team

You will be a part of a small team that researches and develops a variety of computer vision technologies, ranging from Visual Localization/Positioning to SLAM to 3D reconstruction. These technologies power user-facing products within Apple Maps and beyond. To achieve this, you will help develop novel methods that combine 3D geometry and machine learning in innovative ways. Develop novel methods for various computer vision problems, including image and lidar based slam, structure from motion, bundle adjustment, image-based localization, etc. Work with large datasets of different modalities, including aerial, satellite, and ground data. You need to have a strong curiosity about tackling and solving new real-world problems. You would join a team of fast paced and pragmatic problem solvers that are tackling the toughest problems in the field by developing new innovative technology. Strong background in Computer Vision and Machine Learning. Familiarity and hands-on experience with 3D geometry problems (eg: slam, bundle adjustment, 3D reconstruction) and machine learning. Solid programming skills. Masters degree with 2+ years of experience Published papers in top-tier CV/ML conferences (CVPR, ICCV, ECCV, NeurIPS, ICLR, Siggraph, etc.). Experience with training models for feature detection, matching, and pose estimation is appreciated. Knowledge of computer graphics fundamentals is appreciated. Solid C/C++/Python skills. Some experience with GPU/graphics languages, such as CUDA, OpenGL or Metal, is a plus. PhD degree in Compute Vision / Machine Learning / AI / Computer science / Electrical Engineering or related field

For more details click Job Post.