Remote AI Evaluation Writer – Model Feedback & Calibration

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

Job summary

AuraOne is seeking a Technical Writer to join a remote evaluation track. You will review prompts and responses against a quality rubric, providing structured feedback used to retrain the model. This is a contractor role with an hourly pay model, available to candidates eligible to work remotely in the US.

Responsibilities include evaluating model outputs, selecting the stronger response with rationale, labeling issues, and calibrating scores against gold-standard examples each week.

Qualifications

• Prior evaluation, annotation, or human-rater experience in technical writer 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.
• Strong attention to detail and the ability to flag when a prompt is the problem.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate technical writer evaluation model outputs against a versioned rubric and assign severity tags for Technical Writer 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.

Skills

Evaluation experience

Annotation

Inter-rater calibration

Attention to detail

Async availability

Tools

Rubric-based annotation

Job description

AuraOne is seeking a Technical Writer to join a remote evaluation track. You will review prompts and responses against a quality rubric, providing structured feedback used to retrain the model. This is a contractor role with an hourly pay model, available to candidates eligible to work remotely in the US.

Responsibilities include evaluating model outputs, selecting the stronger response with rationale, labeling issues, and calibrating scores against gold-standard examples each week.