AI Image Policy Evaluator & Trainer

Handshake; Seattle (WA); On-site; USD 62,000 - 76,000; Full time

Job summary

Handshake in Seattle, WA is seeking an AI Image Evaluator to help assess prompts and generated images for adherence, quality, and policy compliance. You will review outputs, identify issues, and document clear rationales.

You will compare images, apply rubric-based judgments, and help calibrate models for safety and quality in Handshake AI, working with a cross-functional team in a fast-paced setting.

Qualifications

• Have a trained eye from photography, illustration, design or related field.
• Experience with generative image tools and awareness of their failure modes.
• Experience moderating visual content at scale and applying policy taxonomies.

Responsibilities

• Evaluate generated images against prompts for adherence, composition, realism, and technical defects.
• 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, real-person likeness, IP, and depictions of minors.
• Explain judgments clearly, citing rubric language and image details.
• Write and refine prompts to probe model quality or safety breakdowns.

Skills

Generative image tools

Policy understanding

Attention to detail

Clear writing

Content moderation

Rubric-based reasoning

Tools

Midjourney

Stable Diffusion

ComfyUI

Flux

DALL-E

Ideogram

Job description

Handshake in Seattle, WA is seeking an AI Image Evaluator to help assess prompts and generated images for adherence, quality, and policy compliance. You will review outputs, identify issues, and document clear rationales.

You will compare images, apply rubric-based judgments, and help calibrate models for safety and quality in Handshake AI, working with a cross-functional team in a fast-paced setting.