The mission of the Waymo AI Foundations team is to develop machine learning solutions addressing open problems in autonomous driving, towards the goal of safely operating Waymo vehicles in dozens of cities and under all driving conditions. As part of our work, we also initiate and foster collaborations with other research teams in Alphabet. AI Foundations areas that we are currently focusing on include reinforcement learning, learning from demonstration, generative modeling, Bayesian inference, hierarchical learning, and robust evaluation.

This role follows a hybrid work schedule and reports and reports to a Staff Research Scientist.

You will

• Solve fundamental and applied research problems related to large-scale 3D dynamic scene reconstruction from real-world scenarios, scene synthesis using generative models, and combining reconstructive and generative methods to power AV simulations
• Advance, adapt and scale state-of-the-art ML-based reconstruction methods, such as 3D Gaussian Splatting, to the problem of AV simulation
• Prototype and iterate on various research ideas using Waymo's internal driving data
• Scale and productionize simulation solutions in collaboration with engineering teams across Waymo
• Present research findings to a wide audience within Waymo and Alphabet, with the possibility of publishing results to the research community

You have

• Master’s or PhD degree in Computer Science, Artificial Intelligence, Machine Learning, Deep Learning, or in a similar discipline
• 3+ years of experience in a related field
• In-depth expertise with 3D Gaussian Splatting (3DGS) and/or other learning-based 3D reconstruction methods
• Some experience with generative image/video/world models
• Strong ML software engineering skills in Python with an ability to rapidly prototype solutions
• Familiarity with major ML Frameworks (JAX, Tensorflow, Pytorch)

We prefer

• Publications at top-tier conferences like CVPR/ICCV/ECCV/ICLR/ICML/NeurIPS/IROS/CoRL etc.
• Hands-on experience productionizing and scaling ML solutions beyond the research stage
• Fundamentals in 3D vision and/or computer graphics
• Domain experience in the autonomous vehicle or simulation space