Remote Web Form QA Reviewer and Rubric Analyzer

AuraOne; United States; On-site; USD 34,440 - 82,656; Full time

Job summary

AuraOne is seeking a Web Form Task Research QA Specialist to remotely evaluate evaluation prompts and responses against our quality rubric. You will compare paired outputs, select the stronger answer with rationale, and label edge cases to support retraining of the model.

You will document recurring failure modes, capture ambiguous prompts for rubric updates, and calibrate reviewer scores against gold-standard examples each week.

Qualifications

• Prior evaluation, annotation, or human-rater experience on web form task research QA 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 web form task research QA evaluation model outputs against a versioned rubric and assign severity tags for Web Form Task Research QA Specialist 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

Web Form Task Research QA evaluation

Web research

Source grounding

Browser automation

Form

Task

Job description

AuraOne is seeking a Web Form Task Research QA Specialist to remotely evaluate evaluation prompts and responses against our quality rubric. You will compare paired outputs, select the stronger answer with rationale, and label edge cases to support retraining of the model.

You will document recurring failure modes, capture ambiguous prompts for rubric updates, and calibrate reviewer scores against gold-standard examples each week.