Remote AI Data Evaluator: Video Recorder Evaluation

AuraOne Human Data; United States; Remote; USD 28,000 - 41,000; Full time

Job summary

AuraOne, Inc. is seeking a Video Recorder evaluator to review evaluation prompts and responses against a quality rubric. You will compare outputs, label edge cases, and draft structured feedback for model retraining, all in a remote, US-eligible contractor role.

The position focuses on annotating, tagging severities, and calibrating across batches with a focus on consistency and clarity in reasoning. This contractor role offers flexible hours and requires reliable weekly availability.

Qualifications

• Prior evaluation, annotation, or human-rater experience on video recorder evaluation or adjacent content for Video Recorder (San Francisco) work.
• 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 video recorder evaluation model outputs against a rubric and assign severity tags for Video Recorder (San Francisco) 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

Video Recorder evaluation

Design

Job description

AuraOne, Inc. is seeking a Video Recorder evaluator to review evaluation prompts and responses against a quality rubric. You will compare outputs, label edge cases, and draft structured feedback for model retraining, all in a remote, US-eligible contractor role.

The position focuses on annotating, tagging severities, and calibrating across batches with a focus on consistency and clarity in reasoning. This contractor role offers flexible hours and requires reliable weekly availability.