Korean AI Assistant Reviewer — Conversational Eval (Remote)

AI Trainer Jobs; United States; Remote; USD 58,000 - 80,000; Full time

Job summary

AuraOne seeks a Korean-Language AI Assistant Reviewer – Conversational Evaluation to work remotely as a contractor. Reviewers compare paired outputs against AuraOne's quality rubric, label edge cases, and provide structured feedback to retrain the model.

Responsibilities include evaluating model outputs, selecting the stronger response with rationale, tagging errors, and flagging ambiguous prompts for rubric updates. Compensation is $50 per hour with US remote eligibility.

Qualifications

• Prior evaluation, annotation, or human-rater experience in Korean evaluation tasks.
• Ability to apply multi-page rubrics consistently across batches.
• Clear written reasoning naming issues and rubric clauses.
• 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.
• Compare paired responses and select the stronger answer with 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.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Korean generalist evaluation

Eligibility

Job description

AuraOne seeks a Korean-Language AI Assistant Reviewer – Conversational Evaluation to work remotely as a contractor. Reviewers compare paired outputs against AuraOne's quality rubric, label edge cases, and provide structured feedback to retrain the model.

Responsibilities include evaluating model outputs, selecting the stronger response with rationale, tagging errors, and flagging ambiguous prompts for rubric updates. Compensation is $50 per hour with US remote eligibility.