Preference Taxonomy Reward Model Evaluator

AI Trainer Jobs; United States; Remote; USD 34,000 - 55,000; Full time

Job summary

AuraOne seeks a remote evaluator to review preference taxonomy reward model prompts and responses against its quality rubric. You will compare paired outputs, label edge cases, and write structured feedback for retraining the modeling team.

As a contractor, you will contribute to auditable labels, rationales, and regression cases, producing preference rankings and calibrated human judgments for post-training pipelines. Prior evaluation or moderation experience is valued.

Qualifications

• Experience in evaluation, annotation, or human-rating for preference models.
• Ability to apply multi-page rubrics consistently across long batches.
• Clear written reasoning naming the issue and rubric clause.

Responsibilities

• Evaluate model outputs against a versioned rubric and assign severity tags.
• Compare paired responses and select the stronger with rationale.
• Label hallucinations and unsafe content with structured tags.
• Capture ambiguous prompts for rubric updates.

Skills

Linguistics background

Annotation experience

Inter-rater calibration

Attention to detail

Written reasoning

Job description

Preference Taxonomy Reward Model Evaluator is a remote evaluation track for reviewing preference taxonomy reward model evaluation prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write the kind of structured feedback the modeling team can use to retrain.

Category: RLHF & Human Preference Data · Pay: Hourly rate confirmed after the interview process · Location: Remote — US-eligible · Contractor

Preference Taxonomy Reward Model Evaluator is a remote evaluation track for reviewing preference taxonomy reward model evaluation prompts and responses against AuraOne's quality rubric.

About the role

Preference Taxonomy Reward Model Evaluator is a remote evaluation track for reviewing preference taxonomy reward model evaluation prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write the kind of structured feedback the modeling team can use to retrain.
AI data reviewers help turn preference taxonomy reward model evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.
Produce preference rankings, reward-model feedback, and calibrated human judgment for post-training pipelines.

Responsibilities

• Evaluate preference taxonomy reward model evaluation model outputs against a versioned rubric and assign severity tags for Preference Taxonomy Reward Model Evaluator 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.

Role details

Track Evaluation & annotation Work model Remote · Independent specialist contractor Compensation Hourly rate confirmed after the interview process. Eligible from US

What you should bring

• Prior evaluation, annotation, or human-rater experience on preference taxonomy reward model evaluation or adjacent content for Preference Taxonomy Reward Model Evaluator 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.

Role signals

Example tasks

• Compare two preference taxonomy reward model evaluation model responses to the same prompt and pick the stronger one with rationale.
• Tag an unsafe response with the correct policy category and severity.
• Audit a 50-row batch for rubric consistency and report drift to the program lead.
• Propose a rubric clarification after spotting a recurring failure mode.

Useful experience

• Background in linguistics, content moderation, or trust & safety review.
• Experience with inter-rater agreement metrics and calibration cycles.
• Domain expertise that lets you spot subject-matter errors automated checks miss.

Compensation and schedule

Hourly rate confirmed after the interview process.
Expected arrangement: contractor , with program-defined task volume and review pacing. Placement depends on current program demand and reviewer confirmation.

Skills used in matching

• Model output evaluation
• Rubric-based annotation
• Severity tagging
• Inter-rater calibration
• Preference Taxonomy Reward Model evaluation
• Preference ranking
• RLHF
• Rater calibration
• Preference
• Taxonomy