Video Evaluator (AI Content)

About the role

Video Evaluator (AI Content) is a remote evaluation track for reviewing video evaluation prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write the kind of structured feedback the modeling team can use to retrain.

AI data reviewers help turn video evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.

Review image, video, spatial reasoning, visual grounding, scene understanding, and vision-agent outputs.

Responsibilities

• Evaluate video evaluation model outputs against a versioned rubric and assign severity tags for Video Evaluator (AI Content) assignments.
• Compare paired responses and pick the stronger answer with a written rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route them back to the program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples each week.