AI Model Policy Trainer, Image Evaluation - Seattle Onsite

📋 Description

• Evaluate generated images against their prompts for adherence, composition, realism, style
• Compare images side by side and select the stronger one with a clear, evidence-based rationale
• Classify images against customer content policies covering sexual content, violence, hate symbols
• Select the most defensible classification when an image is genuinely ambiguous, and write concise
• Distinguish 'I do not like this' from 'this fails the prompt' from 'this violates policy,' and keep
• Write and refine prompts that probe where a model's quality or safety behavior breaks down

🎯 Requirements

• You have a trained eye from photography, illustration, concept art, art direction, retouching
• You use generative image tools heavily (Midjourney, Stable Diffusion, ComfyUI, Flux, DALL-E
• You have moderated or reviewed visual content at scale and have applied a policy taxonomy to
• You notice small details: an extra finger, a mismatched shadow, a brand mark, a face that is a
• You can hold a rubric steady across a long session of near-identical images
• You can hold a strong opinion without becoming attached to being right