The Research Scientist in Visual Data and Generative Research at Google will focus on developing innovative solutions in computer vision and generative media. This role involves conducting high-throughput experiments and managing visual data pipelines to enhance the quality of generative video models. The team aims to drive innovation by exploring new technologies and applying them to real-world problems. As part of a collaborative environment, the scientist will also contribute to the wider research community through publications and partnerships.

• PhD or equivalent practical experience in computer vision, machine learning, computer graphics, or generative media.
• Experience in Python and C++.
• Experience with visual data acquisition and curation for 3D vision tasks, such as multi-view video, point clouds, or radiance fields.
• Experience designing and training neural networks, specifically with transformers or diffusion models.

• Design and execute high-throughput strategies to capture high-quality multi-view video and image data from thousands of unique participants and environments.
• Optimize specialized acquisition hardware and optical configurations to extract high-precision ground truth visual data for complex foreground subjects and environmental backgrounds.
• Research and implement methods to fine-tune generative video foundation models on proprietary datasets to produce high-fidelity synthetic video training data.
• Develop automated pipelines that generate high-resolution depth, segmentation, and motion labels from production-grade models.

• Employees at Google are often offered benefits like comprehensive health insurance, 401(k) matching, and flexible work arrangements, among other benefits.