Research Scientist, Vision Language and Multimodal Modeling

At Google, we have a vision of empowerment and equitable opportunity for all Aboriginal and Torres Strait Islander peoples and commit to building reconciliation through Google's technology, platforms and people and we welcome Indigenous applicants. Please see our Reconciliation Action Plan for more information.Minimum qualifications: PhD degree in Computer Science, a related field, or equivalent practical experience.One or more scientific publication submissions for conferences, journals, or public repositories (such as CVPR, ICCV, NeurIPS, ICML, ICLR, etc.). Preferred qualifications: Experience in areas like face anti-spoofing, biometrics, 3D/2.5D vision, facial landmark/pose estimation.Experience with TensorFlow, Flume, common computer vision libraries/frameworks and Android.Interest to build production systems.Excellent software engineering skills (e.g., C++, python, data processing, production backend development, etc.). About The Job As an organization, Google maintains a portfoli...