Korean ChatGPT Evaluation Specialist — Remote Contractor

AuraOne; United States; A distancia; USD 58.000 - 80.000; A tiempo parcial

Descripción de la vacante

AuraOne is seeking a remote evaluation contractor to assess Korean generalist outputs against a quality rubric. You will compare paired responses, label edge cases, and provide structured feedback to aid retraining of the model.

Ideal candidates have prior evaluation or annotation experience on Korean content, with strong written reasoning and attention to detail. Remote work from the US is allowed, with ongoing, async availability of at least 10 hours per week.

Formación

• Prior evaluation/annotation experience on Korean generalist evaluation.
• Experience applying multi-page rubrics across long batches.
• Clear written reasoning naming the issue and rubric clause.
• Strong attention to detail and flagging problematic prompts.
• Reliable async availability for at least 10 hours per week.

Responsabilidades

• 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 to the program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples weekly.
• Document recurring failure modes to guide upcoming training iterations.

Conocimientos

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Korean generalist evaluation

Eligibility

Descripción del empleo

AuraOne is seeking a remote evaluation contractor to assess Korean generalist outputs against a quality rubric. You will compare paired responses, label edge cases, and provide structured feedback to aid retraining of the model.

Ideal candidates have prior evaluation or annotation experience on Korean content, with strong written reasoning and attention to detail. Remote work from the US is allowed, with ongoing, async availability of at least 10 hours per week.