Remote Fact-Check Workflow Evaluator

AuraOne; United States; On-site; USD 55,104 - 96,432; Part time

Job summary

AuraOne is seeking a remote Fact-Check Workflow Task Evaluator to review and label model outputs against a versioned rubric. You will compare paired responses, identify stronger answers, and provide written rationales to support retraining efforts.

The role emphasizes labeling edge cases, tracking recurring failure modes, and calibrating against gold-standard examples on a weekly basis in a contractor capacity. Applicants must be US-authorized and able to work remotely.

Qualifications

• Prior evaluation, annotation, or human-rater experience on fact check workflow task evaluation or adjacent content.
• 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 fact check workflow task evaluation model outputs against a versioned rubric and assign severity tags for 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

Fact Check Workflow Task evaluation

Web research

Source grounding

Browser automation

Fact

Check

Workflow

Tools

Browser automation

Web research

Job description

AuraOne is seeking a remote Fact-Check Workflow Task Evaluator to review and label model outputs against a versioned rubric. You will compare paired responses, identify stronger answers, and provide written rationales to support retraining efforts.

The role emphasizes labeling edge cases, tracking recurring failure modes, and calibrating against gold-standard examples on a weekly basis in a contractor capacity. Applicants must be US-authorized and able to work remotely.