Member of Technical Staff - VLM

📋 Description

• • As a Member of Technical Staff - VLM at Black Forest Labs, you will pioneer the integration of vision-language models directly into the FLUX generative AI stack, advancing foundational research that enhances how creators interact with AI-generated content.
• • Day to day, you will lead the development and training of state-of-the-art multimodal vision-language models, design fine-tuning strategies for creative use cases like captioning and prompt enhancement, research integrations between VLMs and diffusion/flow pipelines, and evaluate emerging architectures to improve generation quality and controllability at scale.
• • Black Forest Labs is the team behind Latent Diffusion, Stable Diffusion, and FLUX — foundational technologies powering tools used by millions worldwide. Headquartered in Freiburg, Germany with a growing presence in San Francisco, the company combines research excellence, open science, and a mission to expand human creativity through technology.
• • In this role, you will push the frontier of multimodal AI research, ship impactful innovations that go beyond fine-tuning, collaborate across research and production boundaries, and contribute to a culture grounded in obsession with quality, low ego, boldness, and kindness — all while advancing your expertise in vision-language modeling at the cutting edge of generative AI.