Research Engineer, Generative Media

• Design, implement, train, and evaluate deep learning architectures—particularly diffusion models and transformers—for image and video synthesis.
• Develop and apply algorithms in computer vision, graphics, and machine learning for Google applications, focusing on computational photography, computational videography, and content creation.
• Conduct both fundamental and applied research to identify and solve creative, novel problems that revolutionize editing, and creation of visual media.
• Leverage deep theoretical and practical knowledge to prototype new technologies that unlock visual experiences for users.
• Build upon our strong track record of publishing graphics venues (with previous publications including Dreambooth, GameNGen, ObjectMate, LightLab, and many more), and successfully transfer these innovations into Google products that reach millions to billions of users.

Minimum qualifications:

• Bachelor’s degree or equivalent practical experience.
  
• 5 years of experience leading a research agenda.
• Experience in designing, training, and evaluating deep generative models (e.g., Diffusion Models, Transformers, GANs) for media synthesis and manipulation (image, video, audio).
  
• Experience with experimentation, dataset curation, eval systems, and building ML pipelines.
• Experience with machine learning, computer vision, and deep learning.
• One of more scientific publication submission(s) for conferences, journals, or public repositories (such as CVPR, ICCV, NeurIPS, ICML, ICLR, etc.).

Preferred qualifications:

• Master's degree or PhD in Computer Science, or a related technical field.
• 3 years of experience working in a complex, matrixed organization involving cross-functional, or cross-business projects.
• 2 years of experience with Machine Learning and Deep Learning frameworks (e.g., TensorFlow, PyTorch).
• Experience or deep domain familiarity with Machine Learning, Computer Vision, Generative AI, or 3D graphics/rendering technologies.

• Bachelor’s degree or equivalent practical experience.
  
• 5 years of experience leading a research agenda.
• Experience in designing, training, and evaluating deep generative models (e.g., Diffusion Models, Transformers, GANs) for media synthesis and manipulation (image, video, audio).
  
• Experience with experimentation, dataset curation, eval systems, and building ML pipelines.
• Experience with machine learning, computer vision, and deep learning.
• One of more scientific publication submission(s) for conferences, journals, or public repositories (such as CVPR, ICCV, NeurIPS, ICML, ICLR, etc.).