Member of Technical Staff - Image / Video Generation
Black Forest Labs · Freiburg (Germany)
CHECKED 13H AGO
Frontier labonsite$146k–$381k
At a glance
Highlights
- Train large-scale diffusion transformers for image and video generation.
- Run rigorous ablations to clarify which architectural choices truly matter.
- Fine-tune models for upscalers, inpainting, outpainting and more.
What they offer
- Equity
- Reasonable travel costs covered for in-person collaboration
Ideal candidate
A generative modeling researcher obsessed with empirical rigor who has trained large diffusion models and cares about distinguishing real progress from tweaks to expand human creativity.
Requirements
- Hands-on experience training large-scale diffusion models for image and video data
- Experience fine-tuning diffusion models for upscalers, inpainting, outpainting or similar tasks
- Deep understanding of evaluating image and video generative models
- Strong proficiency in PyTorch and transformer architectures
- Solid understanding of distributed training including FSDP, low-precision training and model parallelism
- remote policy
- Hybrid in Freiburg or SF 2 days/week or remote with monthly in-person week
- hiring process
- Applications managed with AI-assisted tools; all hiring decisions are made by the team.
Lab profile
About Black Forest Labs
Team behind Stable Diffusion and FLUX building frontier image and video generation models.
What they build
- FLUX image generation models
- FLUX video generation models
Known for
- Pioneers of Latent Diffusion and Stable Diffusion
- State-of-the-art image and video generation
- Models used by millions of creators and businesses
Key facts
- Headquartered in Freiburg, Germany
- Presence in San Francisco