Computer-Use Agent Evaluator

AI Trainer Jobs; United States; Remote; USD 28,000 - 41,000; Part time

Benefits offered by this job

Remote work

Contractor arrangement

Job summary

AI Trainer Jobs is seeking a remote Computer-Use Agent Evaluator to review prompts and model outputs against a versioned rubric. You will label edge cases, provide structured feedback, and help retrain the modeling team.

Responsibilities include evaluating outputs, selecting the stronger answer with rationale, labeling issues, and calibrating scores weekly. This is a remote independent contractor role with hourly compensation after interview.

Qualifications

• Prior evaluation, annotation, or human-rater experience on computer use agent 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 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 computer use agent evaluation model outputs against a versioned rubric and assign severity tags.
• 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 experience

Human-rater experience

Rubric-based annotation

Inter-rater calibration

Attention to detail

Written rationale

Async availability

Linguistics background

Content moderation

Tools

Annotation platforms

Rubric tooling

Job description

About the role

Computer-Use Agent Evaluator is a remote evaluation track for reviewing computer use agent 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 computer use agent 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 computer use agent evaluation model outputs against a versioned rubric and assign severity tags for Computer-Use Agent 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.

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 computer use agent evaluation or adjacent content for Computer-Use Agent Evaluator 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 computer use agent 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
• Computer Use Agent evaluation
• Software engineering and computer use
• AI evaluation
• Rubric writing
• Expert review