Model Grading Failure Analysis Reviewer

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

Job summary

AuraOne seeks a remote Model Grading Failure Analysis Reviewer as an independent contractor. You will review model grading failure analysis prompts and responses, label edge cases, and craft feedback to retrain the modeling team.

This role emphasizes rubric-based evaluation, structured reasoning, and high attention to detail. Eligible applicants are remote and US-eligible, with an hourly rate to be confirmed after the interview.

Qualifications

• Prior evaluation, annotation, or human-rater experience on model grading failure analysis evaluation or adjacent content.

Responsibilities

• Evaluate model grading failure analysis evaluation outputs against a rubric and assign severity tags.
• Compare paired responses and select the stronger answer with a rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route for rubric updates.

Skills

Evaluation experience

Annotation experience

Inter-rater calibration

Job description

Model Grading Failure Analysis Reviewer is a remote evaluation track for reviewing model grading failure analysis 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: Frontier Model Evaluation · Pay: Hourly rate confirmed after the interview process · Location: Remote — US-eligible · Contractor

Model Grading Failure Analysis Reviewer is a remote evaluation track for reviewing model grading failure analysis evaluation prompts and responses against AuraOne's quality rubric.

About the role

Model Grading Failure Analysis Reviewer is a remote evaluation track for reviewing model grading failure analysis 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 model grading failure analysis evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.
Review frontier model outputs. Judge benchmark failures and calibrate other evaluators.

Responsibilities

• Evaluate model grading failure analysis evaluation model outputs against a versioned rubric and assign severity tags for Model Grading Failure Analysis 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.

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 model grading failure analysis evaluation or adjacent content for Model Grading Failure Analysis Reviewer 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 model grading failure analysis 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
• Model Grading Failure Analysis evaluation
• Frontier evaluation
• Rubric calibration
• Failure analysis
• Model
• Grading