Remote Prosody Evaluation Specialist – Model Output QA

AuraOne; United States; On-site; USD 27,552 - 55,104; Part time

Job summary

AuraOne is seeking a Prosody Conversation Evaluator for a remote contractor role. You will review prompts and model outputs, compare paired responses, and write structured feedback using AuraOne's rubric.

The work is conducted remotely from the US and requires clear written reasoning and attention to detail. Responsibilities include labeling failures, tagging unsafe content, and identifying edge cases to help retrain the model.

Qualifications

• Prior evaluation or annotation experience on prosody conversation evaluation or adjacent content.
• Ability to apply multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and rubric clause.

Responsibilities

• Evaluate model outputs against a versioned rubric and assign severity tags.
• Compare paired responses and select the stronger answer with a rationale.
• Label hallucinations, instruction-following failures, and unsafe content.
• Capture ambiguous prompts and route them for rubric updates.
• Calibrate reviewer scores against gold-standard examples weekly.
• Document recurring failure modes for the training team.

Skills

Model eval

Rubric annotation

Severity tagging

Inter-rater calibration

Prosody evaluation

Speech evaluation

Voice QA

Audio review

Prosody

Job description

AuraOne is seeking a Prosody Conversation Evaluator for a remote contractor role. You will review prompts and model outputs, compare paired responses, and write structured feedback using AuraOne's rubric.

The work is conducted remotely from the US and requires clear written reasoning and attention to detail. Responsibilities include labeling failures, tagging unsafe content, and identifying edge cases to help retrain the model.