Korean Formality & Context Evaluator (Remote Contractor)

AuraOne, Inc.; United States; Remote; USD 28,000 - 55,000; Full time

Job summary

AuraOne, Inc. is seeking a Korean Formality Cultural Context Reviewer for a remote contractor role based in the United States.

You will assess Korean generalist outputs against a fixed rubric, tag edge cases, and provide structured feedback to help retrain models. Responsibilities include comparing paired responses, labeling issues with rationale, and calibrating scores against gold-standard examples weekly.

Qualifications

• Prior evaluation, annotation, or human-rater experience on Korean generalist evaluation or adjacent content for Korean Formality Cultural Context Reviewer work.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.

Responsibilities

• Evaluate Korean generalist evaluation model outputs against a versioned rubric and assign severity tags for Korean Formality Cultural Context Reviewer 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

Localization review

Cultural context

Language evaluation

Korean

Formality

Job description

AuraOne, Inc. is seeking a Korean Formality Cultural Context Reviewer for a remote contractor role based in the United States.

You will assess Korean generalist outputs against a fixed rubric, tag edge cases, and provide structured feedback to help retrain models. Responsibilities include comparing paired responses, labeling issues with rationale, and calibrating scores against gold-standard examples weekly.