Remote RLHF Data Reviewer: Consensus & Rubric Feedback

AI Trainer Jobs; United States; Remote; USD 28,000 - 55,000; Full time

Job summary

AuraOne is seeking a Labeler Consensus Preference Data Reviewer for a remote evaluation track. You will review labeler consensus preference data evaluation prompts and responses against our quality rubric, compare paired outputs, and write structured feedback the modeling team can use to retrain.

You will produce preference rankings, reward-model feedback, and calibrated human judgment for post-training pipelines, tagging edge cases and risk signals, while ensuring consistency across long

Qualifications

• Prior evaluation, annotation, or human-rater experience on labeler consensus data evaluation or adjacent content.
• Ability to apply multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.

Responsibilities

• Evaluate labeler consensus preference data evaluation model outputs against a versioned rubric and assign severity tags for Labeler Consensus Preference Data Reviewer 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.

Job description

AuraOne is seeking a Labeler Consensus Preference Data Reviewer for a remote evaluation track. You will review labeler consensus preference data evaluation prompts and responses against our quality rubric, compare paired outputs, and write structured feedback the modeling team can use to retrain.

You will produce preference rankings, reward-model feedback, and calibrated human judgment for post-training pipelines, tagging edge cases and risk signals, while ensuring consistency across long