Member of Technical Staff - VLM

Highlights

• Lead development and training of state-of-the-art VLMs inside the FLUX stack.
• Design VLM fine-tuning for captioning, editing, and prompt enhancement.
• Research VLM and diffusion integrations to improve generation quality.

What they offer

• Equity
• Reasonable travel costs covered for in-person collaboration

Ideal candidate

Frontier-minded researcher-engineer who has shipped or released a pretrained VLM and lives at the research-production boundary. You care that multimodal systems ship, generalize, and expand creativity, not just publish.

Requirements

• Pretrained or significantly advanced a VLM deployed in production or released publicly
• Strong publication record or production track record on multimodal architectures
• Deep understanding of vision-language interaction, alignment and failure modes
• Experience with distributed training at multi-node scale
• Comfortable at research-production boundary focused on shipping and generalization