Remote Tool-Use Reasoning Evaluation Specialist

AuraOne; United States; On-site; USD 55,104 - 82,656; Full time

Job summary

AuraOne is seeking a remote Tool-Use Reasoning Model Evaluation Specialist to review prompts and model outputs against AuraOne's quality rubric. You will compare paired outputs, label edge cases, and write structured feedback for retraining.

This contractor role requires clear written reasoning, meticulous attention to detail, and reliable asynchronous availability for at least 10 hours per week. You will help calibrate scores and document recurring failure modes for the modeling team.

Qualifications

• Prior evaluation, annotation, or human-rater experience on tool-use reasoning model evaluation or adjacent content.
• 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.

Responsibilities

• Evaluate tool-use reasoning model evaluation outputs against a versioned rubric and assign severity tags for assignments.
• Compare paired responses and select 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.

Job description

AuraOne is seeking a remote Tool-Use Reasoning Model Evaluation Specialist to review prompts and model outputs against AuraOne's quality rubric. You will compare paired outputs, label edge cases, and write structured feedback for retraining.

This contractor role requires clear written reasoning, meticulous attention to detail, and reliable asynchronous availability for at least 10 hours per week. You will help calibrate scores and document recurring failure modes for the modeling team.