Minimum qualifications: Bachelor’s degree, or equivalent practical experience. 8 years of experience with software development in one or more programming languages (e.g., Python, C, C++, Java, JavaScript). 5 years of experience leading ML design and optimizing ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning). Experience with computer vision learning techniques, machine learning algorithms (supervised and unsupervised learning, deep learning, reinforcement learning), Generative AI, or Applied AI applications. Preferred qualifications: Master's degree or PhD in Computer Science, or a related technical field. 5 years of experience with one or more of the following: Computer Vision, Reinforcement learning (e.g., sequential decision making), ML infrastructure, or specialization in another ML field. Multiple research publications in top CV/ML conferences (e.g., CVPR/ICCV/ECCV/NIPS/ICLR). Experience working in large-sized engineering and cross-functional teams. Expertise in modeling with TensorFlow, JAX, etc. Strong people management, communication, and problem-solving skills, with the ability to use data to identify systemic issues, form hypotheses, and develop technical proposals. About the job Geo is embarking on a multi-year journey into the future and needs ML/AI engineers to help us navigate to that tomorrow. As a Staff Software Engineer, you will help design and build the freshest and most detailed 3D navigation map using sensor data (e.g., imagery, vehicle telemetry, location data, authoritative data, etc.), large ML models, and more. We need people with a collaborative mindset who can work across organizations including Geo's Basemap, Infrastructure, Consumer and Automotive teams along with Cloud and Research product areas to enable Google's future map making technologies. The correct candidate will step into a technical leadership role, working with junior engineers and generalist colleagues to deliver these products. Come help us build the future of maps! To learn more about Geo, check out our video. The Geo team is focused on building the most accurate, comprehensive, and useful maps for our users, through products like Maps, Earth, Street View, Google Maps Platform, and more. Every month, more than a billion people rely on Maps services to explore the world and navigate their daily lives. The Geo team also enables developers to use the power of Google Maps platforms to enhance their apps and websites. As they plot a course for the future of mapping, they are solving complex computer science problems, designing beautiful and intuitive product experiences, and improving our understanding of the real world. Individual pay is determined by factors including job-related skills, experience, and relevant education or training. US: $207000 - $301000 (USD) + 20% bonus target + equity + benefits Learn more about benefits at Google. Responsibilities Lead the design, development, and deployment of ML models to map 15+ road and lane attributes (such as surface type, lane count, medians) from Google’s extensive signal corpus (imagery, driving telemetry, vehicle sensor observations, location data, waze, etc.). Drive model development, data curation, evaluation, and prototype novel concepts for vision learning, fusing signals from multiple sensors/sources. Stay current with the latest advancements in ML research and translate them into practical solutions for real-world business problems. Evaluate, adapt, and deploy the latest in vision transformers and GenAI to solve problems without textbook answers. Collaborate closely with other Engineers, Product Managers, Analysts, and Operations teams to define requirements, integrate ML solutions, and drive impact on map data quality. Provide technical leadership and mentorship to junior engineers on the team.