Member of Technical Staff - Post Training
Black Forest Labs is seeking a Member of Technical Staff to lead the post-training pipeline for our multimodal models, including image, editing, and video applications. As a key player in our research team, you will drive the transformation of foundation models into production-ready products, ensuring they align with human intent and aesthetic judgment. Our company is renowned for pioneering technologies like Latent Diffusion, Stable Diffusion, and FLUX, which have revolutionized image and video creation worldwide.
In this role, you will be responsible for the entire post-training process, encompassing data curation, reward modeling, fine-tuning, preference optimization, distillation, safety tuning, evaluation, and deployment. You will advance techniques across the post-training stack, such as supervised fine-tuning (SFT), reinforcement learning from human feedback (RLHF), reinforcement learning from AI feedback (RLAIF), direct preference optimization (DPO), and reward modeling. Additionally, you will develop personalization and customization capabilities, enabling users to adapt our models to their unique creative styles. Designing and maintaining high-throughput fine-tuning and evaluation infrastructure to support rapid iteration across the research team will also be a key aspect of your day-to-day work.
The ideal candidate will have extensive experience owning post-training for frontier generative models through release, with measurable quality improvements on human preferences or standard benchmarks. A deep understanding of the entire post-training stack, including reward modeling, preference learning, RLHF/RLAIF, and personalization, is essential. Proficiency in PyTorch and the ability to write research code that others can build upon are required. Experience with distillation methods, such as LADD, DMD, or consistency models, or with building high-throughput evaluation pipelines, is a strong plus. A bias toward shipping measurable model-quality improvements that reach users, rather than focusing solely on academic publications, is highly valued.
We offer a collaborative and dynamic work environment grounded in four core values: obsession with research excellence, low ego, boldness in taking ambitious bets, and kindness in treating each other with genuine warmth. Our distributed team operates with real offices in Freiburg, Germany, and San Francisco, USA, with flexible arrangements to accommodate in-person collaboration. We cover reasonable travel costs to facilitate this, ensuring accessibility for all team members.
Joining Black Forest Labs means contributing to cutting-edge research that powers tools used by millions of creators, developers, and businesses worldwide. You will have the opportunity to push the state of the art in aligning generative models to human intent, working alongside a team that values depth over noise, collaboration over hero culture, and honest technical conversations over hype.