Remote Mobile AI Evaluation Specialist

AuraOne; United States; On-site; USD 34,000 - 69,000; Part time

Job summary

AuraOne is seeking a Remote Mobile Engineering AI Evaluator to review evaluation prompts and responses against our quality rubric. This contractor role involves comparing paired outputs, labeling edge cases, and drafting structured feedback for the modeling team to retrain.

You will work asynchronously for at least 10 hours per week, maintain calibration with gold-standard examples, and help surface recurring failure modes.

Qualifications

• Experience evaluating, annotating, or acting as a human rater for mobile engineering AI evaluation or related content.
• Ability to apply multi-page rubrics consistently across large batches.
• Clear written reasoning naming the issue and the rubric clause.
• Strong attention to detail and the ability to flag when prompts are problematic.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate mobile engineering AI evaluation model outputs against a versioned rubric and assign severity tags for Mobile Engineering AI 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.
• Maintain reviewer-quality scores by calibrating against gold-standard examples each week.
• Document recurring failure modes so the modeling team can target them in the next training run.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Mobile Engineering AI evaluation

Software engineering basics

AI evaluation

Rubric writing

Expert review

Job description

AuraOne is seeking a Remote Mobile Engineering AI Evaluator to review evaluation prompts and responses against our quality rubric. This contractor role involves comparing paired outputs, labeling edge cases, and drafting structured feedback for the modeling team to retrain.

You will work asynchronously for at least 10 hours per week, maintain calibration with gold-standard examples, and help surface recurring failure modes.