Black Forest Labs

Research role focused on leading large-scale pretraining experiments for multimodal foundation models (image, video, audio), involving architecture, objective functions, and training algorithms. Requires prior experience leading pretraining for production models and strong distributed training skills.

Research role focused on developing and integrating state-of-the-art vision-language models (VLMs) into the FLUX generative AI stack, innovating on architectures and improving multimodal understanding for enhanced generation quality and controllability.

Research role focused on training and fine-tuning large-scale diffusion models for image and video generation, involving rigorous experimentation, ablation studies, and understanding speed-quality tradeoffs in production settings.