Remote Screenshot Understanding Evaluator

AuraOne; United States; Remote; USD 27,552 - 55,104; Full time

Job summary

AuraOne is seeking a remote Screenshot Understanding Model Evaluator to review evaluation prompts and responses against our quality rubric. As an independent contractor, you will compare paired outputs, label edge cases, and provide structured feedback to help retrain the modeling team.

You will maintain steady weekly calibration, document recurring failures, and ensure accurate severity tagging. Prior evaluation or annotation experience is preferred.

Qualifications

• Prior evaluation, annotation, or human-rater experience on screenshot understanding model evaluation or adjacent content.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate outputs against a versioned rubric and assign severity tags.
• Compare paired responses and choose the stronger with rationale.
• Label hallucinations, instruction-following failures, and unsafe content with tags.
• Capture ambiguous prompts and route to program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples weekly.
• Document recurring failure modes for future training.

Skills

Model evaluation

Rubric annotation

Severity tagging

Inter-rater calibration

Multimodal evaluation

Cross-modal reasoning

Grounding review

Screenshot proficiency

Attention to detail

Work independence

Job description

AuraOne is seeking a remote Screenshot Understanding Model Evaluator to review evaluation prompts and responses against our quality rubric. As an independent contractor, you will compare paired outputs, label edge cases, and provide structured feedback to help retrain the modeling team.

You will maintain steady weekly calibration, document recurring failures, and ensure accurate severity tagging. Prior evaluation or annotation experience is preferred.