The role is focused on developing Pinterest Canvas, an internal text-to-image generative model within the Pinterest Labs organization. The visual modeling team is responsible for building large-scale generative models using Pinterest's rich visual-text dataset. Candidates will work collaboratively in a small group to prototype new model architectures and contribute to the overall visual generative strategy. This position emphasizes hands-on experience with diffusion models and mentoring junior researchers.

• 5+ years of industry computer vision experience.
• M.S. or PhD in Machine Learning, Computer Science, or related areas.
• Experience working with generative computer vision models, preferably various forms of diffusion models.

• Prototype new model architectures for Pinterest Canvas, our internal text-to-image generative model.
• Read research papers, participate in group discussions, and help brainstorm our overall visual generative strategy.
• Help with the collection of relevant visual training data for Pinterest Canvas.
• Publish and publicize your work via conferences, paper submissions, blog posts, etc.
• Mentor more junior researchers or research interns within the Pinterest Labs organization.