Remote Korean AI Evaluation Specialist

AI Trainer Jobs; United States; Remote; USD 34,000 - 55,000; Full time

Job summary

AI Trainer Jobs in the United States is seeking a remote HR Documents Specialist (Korean) to review prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write structured feedback to retrain the model.

You will help turn Korean evaluation outputs into auditable labels, rationales, and regression cases while evaluating frontier model outputs, judging benchmarks, and calibrating other evaluators.

Qualifications

• Prior evaluation, annotation, or human-rater experience on Korean content.
• Clear written reasoning that cites rubric clauses.
• Reliable async availability for at least 10 hours per week.
• Background in linguistics, content moderation, or trust & safety review.

Responsibilities

• Evaluate Korean generalist evaluation model outputs against a versioned rubric and assign severity tags for HR Documents Specialist (Korean) 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.

Job description

AI Trainer Jobs in the United States is seeking a remote HR Documents Specialist (Korean) to review prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write structured feedback to retrain the model.

You will help turn Korean evaluation outputs into auditable labels, rationales, and regression cases while evaluating frontier model outputs, judging benchmarks, and calibrating other evaluators.