Member of Technical Staff - Image / Video Generation
Experience Requirements:
Hands-on experience training large-scale diffusion models for image and video data
Experience fine-tuning diffusion models for specialized applications
Deep understanding of effectively evaluating image and video generative models
Strong proficiency in PyTorch, transformer architectures, and deep learning ecosystem
Solid understanding of distributed training techniques (FSDP, low precision, parallelism)
Other Requirements:
Experience writing Triton kernels
Proficiency with profiling and debugging tools like Nsight
Understanding of performance characteristics of architectural choices at scale
Published research in generative models
Responsibilities:
Train large-scale diffusion transformer models for image and video data
Rigorously ablate design choices via isolation of variables and controlled experiments
Reason about speed-quality tradeoffs of neural network architectures in production
Fine-tune diffusion models for specialized applications (upscalers, inpainting)
Shape research direction by communicating experimental results
Show more details
