Remote Web Safety Evaluator: Task Review & Labeling

AuraOne

United States

On-site

USD 34,440 - 55,104

Full time

14 days+
Application generator

A complete application in a minute — tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

AuraOne is seeking a remote Web Agent Safety Task Evaluator to review prompts and model outputs against our safety rubric, labeling edge cases and writing structured feedback to help retrain the modeling team.

You will compare paired responses, assign severity tags, and document recurring failure modes while maintaining calibration against gold-standard examples. This contractor role requires reliably asynchronous availability for at least 10 hours per week.

Qualifications

  • Prior evaluation, annotation, or human-rater experience on web agent safety task evaluation or adjacent content.
  • Clear written reasoning that names the issue and the rubric clause applied.
  • Reliable async availability for at least 10 hours per week.

Responsibilities

  • Evaluate web agent safety task evaluation model outputs against a versioned rubric and assign severity tags for Web Agent Safety Task Evaluator 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.

Skills

Web Agent Safety evaluation
Rubric-based annotation
Inter-rater calibration
Clear written reasoning
Attention to detail

Tools

Browser automation

Job description

AuraOne is seeking a remote Web Agent Safety Task Evaluator to review prompts and model outputs against our safety rubric, labeling edge cases and writing structured feedback to help retrain the modeling team.

You will compare paired responses, assign severity tags, and document recurring failure modes while maintaining calibration against gold-standard examples. This contractor role requires reliably asynchronous availability for at least 10 hours per week.

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Remote Web Browsing Task Evaluator & Quality Feedback Lead
Remote Web Browsing Task Evaluator & Quality Feedback Lead

AuraOne • United States

On-site
USD 34,440 - 55,104
Remote Human Data Evaluator & Rubric Reviewer
Remote Human Data Evaluator & Rubric Reviewer

AuraOne • United States

On-site
USD 34,000 - 55,000
Remote Web Form QA Reviewer and Rubric Analyzer
Remote Web Form QA Reviewer and Rubric Analyzer

AuraOne • United States

On-site
USD 34,440 - 82,656
Remote Crisis Response Safety Risk Evaluator & Rubric Lead
Remote Crisis Response Safety Risk Evaluator & Rubric Lead

AuraOne • United States

On-site
USD 34,440 - 48,216
Remote Web QA Evaluator - Research & Rubric Specialist
Remote Web QA Evaluator - Research & Rubric Specialist

AuraOne • United States

On-site
USD 55,104 - 96,432
Remote Social Engineering Security Evaluator
Remote Social Engineering Security Evaluator

AuraOne • United States

On-site
USD 55,104 - 82,656
Remote contractor
US-eligible
Contractor arrangement
Remote AI Evaluation & Feedback Specialist
Remote AI Evaluation & Feedback Specialist

AuraOne • United States

On-site
USD 55,000 - 110,000
Remote work
US-eligible
Contractor position
Remote Robot Safety Task Evaluator & Rubric Auditor
Remote Robot Safety Task Evaluator & Rubric Auditor

AuraOne • United States

On-site
USD 55,104 - 82,656
Remote Cloud Security Evaluator: Model Feedback & Review
Remote Cloud Security Evaluator: Model Feedback & Review

AuraOne • United States

On-site
USD 55,104 - 96,432
Remote Visual QA Evaluator & Rubric Auditor
Remote Visual QA Evaluator & Rubric Auditor

AuraOne • United States

On-site
USD 34,440 - 55,104