Member of Technical Staff - Image / Video Generation

📋 Description

• Train large-scale diffusion transformer models for image and video data.
• Rigorously ablate design choices and communicate insights to shape research.
• Assess speed-quality tradeoffs of architectures in production-like settings.
• Fine-tune diffusion models for specialized tasks like upscalers, inpainting/outpainting.

🎯 Requirements

• Hands-on experience training large-scale diffusion models for image/video data.
• Fine-tuning diffusion models for domain-specific tasks (upscaling, inpainting, outpainting).
• Deep understanding of evaluating image/video generative models and quality metrics.
• Strong proficiency in PyTorch, transformer architectures, and modern DL tooling.
• Distributed training knowledge: FSDP, low precision, model parallelism.

🎁 Benefits

• Distributed team with offices in Freiburg and SF; in-person collaboration supported.
• Reasonable travel costs covered for in-person weeks.
• Base annual salary EU €130,000-€340,000 + Equity.