Remote Voice Acting QA Reviewer (US/Canada Accent)

AuraOne, Inc.; United States; À distance; USD 28 000 - 55 000; Plein temps

Résumé du poste

AuraOne, Inc. is seeking remote contractor reviewers to assess voice actress outputs against a versioned rubric. You will compare paired responses, label edge cases, and write rationales to aid model retraining.

Responsibilities include tagging unsafe content, capturing ambiguous prompts, and calibrating against gold-standard examples weekly. Prior evaluation experience and strong written reasoning are required.

Qualifications

• Prior evaluation, annotation, or human-rater experience on voice actress evaluation or adjacent content for Voice Actress (US or Canada Accent) work.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.
• Comfort applying multi-page rubrics consistently across long batches.

Responsabilités

• Evaluate voice actress evaluation model outputs against a versioned rubric and assign severity tags for Voice Actress (US or Canada Accent) 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.

Connaissances

Evaluation experience

Rubric-based annotation

Severity tagging

Inter-rater calibration

Voice actress evaluation

Description du poste

AuraOne, Inc. is seeking remote contractor reviewers to assess voice actress outputs against a versioned rubric. You will compare paired responses, label edge cases, and write rationales to aid model retraining.

Responsibilities include tagging unsafe content, capturing ambiguous prompts, and calibrating against gold-standard examples weekly. Prior evaluation experience and strong written reasoning are required.