The visual modeling team at Pinterest is seeking research engineers and scientists to advance vision-centric large language models (VLMs). This role focuses on developing new model architectures and evaluation benchmarks tailored to visual capabilities. Candidates will work with unique visual-text datasets to create generative models for production. Collaboration with a small team of engineers and product prototyping is essential to enhance Pinterest's core product.

• Research engineers and scientists with experience in generative computer vision models.
• A minimum of 2 years of industry experience in computer vision.
• An M.S. or PhD in Machine Learning, Computer Science, or related areas.

• Prototype new model architectures for Pinterest VLMs.
• Develop new evaluation benchmarks for vision-centric capabilities.
• Read research papers and participate in group discussions to brainstorm visual generative strategies.
• Assist in the collection of relevant visual training data for Pinterest Canvas.
• Publish and publicize work through conferences, paper submissions, and blog posts.