Remote Voice Evaluation Expert (Contractor)

AuraOne, Inc.; United States; A distancia; USD 25.000 - 39.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Background in linguistics

Experience with inter-rater agreement

Domain expertise in trust & safety

Descripción de la vacante

AuraOne, Inc. is seeking a remote contractor to review voice actors evaluation prompts and responses, applying a versioned rubric to assign severity tags and provide structured feedback for retraining.

You will compare paired outputs, label edge cases, and document recurring failures to help improve the modeling team’s training runs. Strong written reasoning and attention to detail are essential, with at least 10 hours per week available.

Formación

• Prior evaluation, annotation, or human-rater experience on voice actors evaluation or adjacent content for Voice Actors work.
• Comfort applying multi-page rubrics consistently across long batches.
• 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.

Responsabilidades

• Evaluate voice actors evaluation model outputs against a versioned rubric and assign severity tags for Voice Actors 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.

Conocimientos

Evaluation experience

Rubric-based annotation

Clear written reasoning

Attention to detail

Async availability

Descripción del empleo

AuraOne, Inc. is seeking a remote contractor to review voice actors evaluation prompts and responses, applying a versioned rubric to assign severity tags and provide structured feedback for retraining.

You will compare paired outputs, label edge cases, and document recurring failures to help improve the modeling team’s training runs. Strong written reasoning and attention to detail are essential, with at least 10 hours per week available.