The Waymo Mapping team's goal is to build a high resolution map of the world to support safe autonomous driving. We work on creating the map using a combination of automatic and manual techniques and build the infrastructure to store, process, and distribute the map. Our team collaborates with several other Waymo teams that consume map data.

In this role, you will:

• Design, train, and deploy machine learning models to automate the creation of Waymo's HD maps, unlocking scale for the Waymo Driver.
• Apply and advance state-of-the-art ML techniques, including Vision-Language Models (VLMs) and other Generative AI approaches, to pioneer new solutions in mapping automation.
• Own the complete model development lifecycle, from data mining and processing to model training, evaluation, validation, and productionization.
• Collaborate closely with partner ML teams, such as Waymo Perception and Waymo AI Foundations, to adapt cutting-edge research into scalable, reliable, and production-grade solutions.

You have:

• 4+ years of hands-on experience in Machine Learning, with a strong focus on computer vision and/or deep learning.
• Proficiency in at least one major deep learning framework (e.g., TensorFlow, PyTorch, JAX).
• Demonstrated experience owning problems end-to-end and working across various parts of the systems stack to deliver results.
• B.S. in Computer Science, a similar technical field, or equivalent practical experience.

It's a Bonus if you have:

• M.S. or Ph.D. degree in Computer Science or a related discipline.
• Familiarity with foundation models and techniques for model adaptation (e.g., few-shot learning, transfer learning, domain adaptation).
• A track record of publications in top-tier ML/CV conferences (e.g., NeurIPS, ICML, CVPR, ICCV, ECCV).
• Experience with C++.
• Direct experience with mapping or GIS is a bonus but not required.