Black Forest Labs seeks a Staff-level Member of Technical Staff to pioneer the integration of vision-language models into the FLUX stack, focusing on novel architectures and production-ready multimodal systems.
This position centers on advancing how generative AI interacts with visual content by embedding vision-language models directly into the FLUX generation pipeline. The role demands a senior individual contributor who will design innovative architectural approaches rather than simply applying existing solutions, ensuring models are more powerful, controllable, and aligned with creative workflows.
Responsibilities
- Architect and train cutting-edge multimodal vision-language models within the FLUX ecosystem, focusing on novel structural innovations.
- Develop specialized fine-tuning methodologies to adapt vision-language models for creative tasks such as image captioning, editing instructions, and prompt refinement.
- Investigate how vision-language and large language model capabilities can be integrated with diffusion and flow pipelines to enhance output quality and user control.
- Assess new multimodal research and implement the most promising findings to drive practical advancements in the generation stack.
Requirements
- Demonstrated experience pretraining or significantly advancing a vision-language model that has been deployed in production or released publicly.
- A strong publication history or clear production track record demonstrating the ability to push the boundaries of multimodal architectures.
- Comprehensive knowledge of vision-language representation interactions, including tokenization, alignment, grounding, cross-modal attention mechanisms, and common failure modes.
- Proven experience conducting distributed training across multiple nodes.
- Ability to operate effectively at the intersection of research and production, with a focus on shipping work that generalizes well.
Nice to have
- Familiarity with diffusion or flow-based generative models, particularly understanding how autoregressive and diffusion paradigms can be combined.
What the company offers
- Annual base salary between €130,000 and €340,000, supplemented by equity.
- Reimbursement for reasonable travel expenses related to in-person meetings.
About the company
Black Forest Labs operates as a frontier research lab dedicated to research excellence, open science, and developing technology that expands human creativity. The team values deep scientific inquiry, beautiful product design, and a low-ego culture where the best ideas prevail regardless of origin. The company encourages bold, ambitious bets and prioritizes kindness and genuine warmth among team members, treating people above politics.
- Focus on research excellence, open science, and expanding human creativity.
- Distributed team structure with offices in Freiburg and SF, requiring hybrid in-person attendance.
- Commitment to deep science and beautiful product design.
- Low-ego environment where the best idea wins and credit is shared.
- Bold approach to ambitious projects, shipping without waiting for perfect conditions.
- Kindness and genuine warmth, prioritizing people over politics.
Quelle: öffentlich zugängliche Karriereseite des Arbeitgebers. Batchly ist nicht der Arbeitgeber und steht nicht notwendigerweise in einem Vertragsverhältnis mit dem Unternehmen.