Remote Visual AI Evaluation Specialist

AuraOne; United States; Remote; USD 41,000 - 55,000; Full time

Job summary

AuraOne is seeking an Image Reasoning Generalist — Visual AI Evaluation contractor to review model outputs against a standard rubric. This remote, US-eligible role focuses on labeling edge cases, writing structured feedback, and helping retrain the system.

You will compare paired outputs, tag issues, and calibrate against gold-standard examples, committing to at least 10 hours per week. Compensation is $35 per hour.

Qualifications

• Prior evaluation, annotation, or human-rater experience on image reasoning generalist 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 image reasoning generalist evaluation model outputs against a versioned rubric and assign severity tags for Image Reasoning Generalist — Visual AI Evaluation (Remote, $35/hr) 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.
• Document recurring failure modes so the modeling team can target them in the next training run.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Image Reasoning Generalist evaluation

Job description

AuraOne is seeking an Image Reasoning Generalist — Visual AI Evaluation contractor to review model outputs against a standard rubric. This remote, US-eligible role focuses on labeling edge cases, writing structured feedback, and helping retrain the system.

You will compare paired outputs, tag issues, and calibrate against gold-standard examples, committing to at least 10 hours per week. Compensation is $35 per hour.