Remote AI Agent Evaluator & Rubric Specialist

AuraOne; United States; Remote; USD 28,000 - 55,000; Full time

Job summary

AuraOne is seeking an AI Agent Evaluator to work remotely as a Contractor. You will review AI agent outputs, apply a versioned rubric, and provide structured feedback, labels, and rationales to help retrain models.

Responsibilities include comparing paired responses, tagging content issues, and documenting recurring failure modes for calibration. The role is remote and US-eligible with an hourly rate paid after interview.

Qualifications

• Experience in evaluating AI agent outputs using structured rubrics.
• Ability to write clear rationale names for rubric clauses.
• Attention to detail and the ability to flag prompt issues.

Responsibilities

• Evaluate AI agent outputs against a rubric and assign severity tags.
• Compare paired responses and justify the stronger answer with rationale.
• Label hallucinations, instruction-following failures, and unsafe content with tags.
• Document prompts and rubric gaps for rubric updates.
• Calibrate reviewer quality against gold-standard examples weekly.
• Record recurring failure modes for model retraining.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

AI Agent evaluation

AI model evaluation

Job description

AuraOne is seeking an AI Agent Evaluator to work remotely as a Contractor. You will review AI agent outputs, apply a versioned rubric, and provide structured feedback, labels, and rationales to help retrain models.

Responsibilities include comparing paired responses, tagging content issues, and documenting recurring failure modes for calibration. The role is remote and US-eligible with an hourly rate paid after interview.