Tech Stack

Description

You will train large-scale diffusion transformer models for image and video data, rigorously ablate design choices, and fine-tune models for specialized applications like upscalers and inpainting. This role focuses on running experiments that clarify which architectural choices matter, advancing generative AI for millions of creators worldwide.

Requirements

• Hands-on experience training large-scale diffusion models for image and video
• Experience fine-tuning diffusion models for specialized applications
• Deep understanding of evaluating image and video generative models
• Strong proficiency in PyTorch, transformer architectures, and modern deep learning
• Solid understanding of distributed training techniques (FSDP, low precision, model parallelism)

Responsibilities

• Train large-scale diffusion transformer models for image and video data
• Rigorously ablate design choices and communicate results to shape research direction
• Analyze speed-quality tradeoffs of neural network architectures in production
• Fine-tune diffusion models for specialized applications such as upscalers and inpainting