Remote AI Image Evaluation & Policy Trainer

Handshake; Seattle (WA); Remote; USD 128,943,000 - 157,046,000; Full time

Job summary

Handshake is seeking an AI Image Evaluator to assess generated images against prompts, focusing on adherence, composition, realism, and technical quality. You will compare pairs, justify decisions with rubric-based reasoning, and classify content per policy guidelines.

Strong applicants will have a trained eye for visual detail, experience with generative tools (Midjourney, Stable Diffusion, DALL-E), and the ability to document precise rationales under time pressure.

Qualifications

• You can articulate why one image is better than another.
• You can identify policy violations and classify accordingly.
• You can balance rubric text with customer expectations.

Responsibilities

• Evaluate generated images against prompts for adherence, composition, realism, style, and defects.
• Compare images side by side and select the stronger one with a clear, evidence-based rationale.
• Classify images against customer policies for sexual content, violence, IP, and real-person likeness.
• Write concise rationales citing rubric language and visual details when decisions are ambiguous.
• Distinguish between personal preference and policy constraints and document judgments clearly.

Skills

Critical eye for images

Image evaluation

Policy interpretation

Clear written reasoning

Tools

Midjourney

Stable Diffusion

DALL-E

Job description

Handshake is seeking an AI Image Evaluator to assess generated images against prompts, focusing on adherence, composition, realism, and technical quality. You will compare pairs, justify decisions with rubric-based reasoning, and classify content per policy guidelines.

Strong applicants will have a trained eye for visual detail, experience with generative tools (Midjourney, Stable Diffusion, DALL-E), and the ability to document precise rationales under time pressure.