• Design, train, and deploy deep learning models for lane marking and road feature detection using camera, LiDAR, and other sensor data. • Develop transformer-based architectures and leverage other modern deep learning techniques for spatial-temporal perception and HD map updating. • Handle complex scenarios such as poorly painted lanes and temporary construction areas in dynamic weather conditions. • Collaborate with perception, localization, and planning teams to integrate learning-based map components into the autonomous driving system. • Conduct data analysis, dataset curation, and annotation for model training and evaluation.