Korean QA & Evaluation Specialist (Remote)

AuraOne; United States; On-site; USD 34,000 - 55,000; Full time

Job summary

AuraOne is seeking a Korean Language Expert to remotely assess prompts and responses, applying a versioned rubric to provide auditable labels and rationale. This contractor role requires careful, consistent annotation and weekly calibration to maintain high reviewer quality.

You'll compare outputs, tag issues, and route ambiguities for rubric updates, contributing to robust retraining data. Hourly contract work from the US.

Qualifications

• Prior evaluation, annotation, or human-rater experience on korean generalist evaluation or adjacent content.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Reliable async availability for at least 10 hours per week.
• Comfort applying multi-page rubrics consistently across long batches.

Responsibilities

• Evaluate korean generalist evaluation model outputs against a versioned rubric and assign severity tags for Korean Language Expert 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

Korean language evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Korean generalist evaluation

Job description

AuraOne is seeking a Korean Language Expert to remotely assess prompts and responses, applying a versioned rubric to provide auditable labels and rationale. This contractor role requires careful, consistent annotation and weekly calibration to maintain high reviewer quality.

You'll compare outputs, tag issues, and route ambiguities for rubric updates, contributing to robust retraining data. Hourly contract work from the US.