Creative Tech Researcher V

What you'll do

• Develop and optimize model architectures for image and video generation and editing.
• Prepare and organize data for training large-scale image and video generation models.
• Implement efficient distributed training and data loading infrastructure on large-scale clusters.
• Conduct cross-team evaluations to gather feedback and build representative benchmarks.
• Ensure high quality across all model outputs through rigorous evaluation frameworks.
• Integrate groundbreaking research into the global production ecosystem for content production tools.

What we're looking for

• Deep understanding of deep learning fundamentals including Transformers and Diffusion models.
• Skill in data preparation and curation for large-scale model training.
• Proven experience in distributed training and inference on large clusters.
• Ability to develop and optimize architectures for image and video generation.
• Experience building evaluation frameworks and representative benchmarks for model outputs.
• Ability to operate effectively in a fast-paced, innovative culture.
• Experience delivering high-impact products or open-source projects is preferred.