Member of Technical Staff - Image / Video Generation

Black Forest Labs; Freiburg im Breisgau; Vor Ort; EUR 60.000 - 80.000; Vollzeit

Zusammenfassung

A cutting-edge startup in Freiburg im Breisgau is seeking a strong researcher to work on model training and development for generative image and video models. The ideal candidate will have experience with large-scale Diffusion models, a deep understanding of evaluating generative models, and proficiency in PyTorch. Responsibilities include training models, communicating results, and assessing quality trade-offs. This position offers an opportunity to work at the forefront of AI technology with a passionate team.

Qualifikationen

• Experience with training large scale Diffusion models for image and video applications.
• Deep understanding of evaluating image and video generative models.

Aufgaben

• Train large scale Diffusion models for image and video.
• Communicate results and design choices with the team.
• Evaluate speed and quality trade-offs of architectures.

Kenntnisse

Training large scale Diffusion models for image and video data

Strong proficiency in PyTorch

Deep understanding of training techniques

Experience with profiling and debugging

Tools

PyTorch

Nsight

Jobbeschreibung

Black Forest Labs is a cutting‑edge startup pioneering generative image and video models. Our team, which invented Stable Diffusion, Stable Video Diffusion, and FLUX.1, is currently seeking a strong researcher to work on model training and development.

Role:

• Training large scale Diffusion (transformer) models for image and video
• Rigorously ablating design choices and communicating results & decisions with the broader team
• Reasoning about the speed and quality trade‑offs of neural network architectures

Ideal Experiences:

• Training large scale Diffusion models for image and video data
• Finetuning Diffusion models for image and video applications, such as image and video upscalers, in and out painting models, etc.
• Deep understanding of how to effectively evaluate image and video generative models
• Strong proficiency in PyTorch, transformer models and other NN architectures
• Deep understanding of training techniques such as FSDP, low precision training, and model parallelism

Nice to have:

• Experience with writing forward and backward Triton kernels and ensuring their correctness while considering floating point errors
• Profiling, debugging, and optimizing single and multi‑GPU operations using tools such as Nsight or stack trace viewers