Member of Technical Staff Image Video Generation

You will train and fine-tune large-scale image and video diffusion models. You will run controlled ablation experiments, evaluate architecture tradeoffs, debug distributed training, optimize GPU operations, and communicate research findings that guide future model development.

Responsibilities

• Train large-scale diffusion transformer models for image and video
• Run controlled ablation experiments and communicate findings
• Evaluate speed-quality tradeoffs in neural-network architectures
• Fine-tune diffusion models for specialized applications
• Debug distributed training issues
• Evaluate image and video generative models

Requirements

• Experience training large-scale diffusion models for image and video
• Experience fine-tuning diffusion models for specialized applications
• Understanding of image and video generative-model evaluation
• Proficiency with PyTorch, transformer architectures, and deep learning
• Understanding of FSDP, low-precision training, and model parallelism

Benefits

• Equity
• Reasonable travel costs for required in-person time