Korean Bilingual Evaluator & Rubric QA (Remote)

AuraOne; United States; On-site; USD 20,000 - 29,000; Part time

Job summary

AuraOne is seeking a Remote Bilingual Writer - Korean (South Korea) contractor. You will review Korean outputs against the quality rubric, label issues, and provide structured feedback for retraining the model.

The role requires disciplined rubric application and strong attention to detail. Responsibilities include comparing responses, tagging policy violations, routing ambiguous prompts for rubric updates, and calibrating scores weekly.

Qualifications

• Prior evaluation or annotation experience on Korean generalist evaluation.
• Ability to apply multi-page rubrics consistently.
• 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 Korean generalist evaluation model outputs against a versioned rubric and assign severity tags for Bilingual Writer - Korean (South Korea) 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

Korean generalist evaluation

Job description

AuraOne is seeking a Remote Bilingual Writer - Korean (South Korea) contractor. You will review Korean outputs against the quality rubric, label issues, and provide structured feedback for retraining the model.

The role requires disciplined rubric application and strong attention to detail. Responsibilities include comparing responses, tagging policy violations, routing ambiguous prompts for rubric updates, and calibrating scores weekly.