Remote Browser Automation Evaluator: Feedback

AuraOne, Inc.; United States; Remote; USD 34,000 - 62,000; Full time

Job summary

AuraOne, Inc. is seeking a remote Browser Automation Task Evaluator to review prompts and responses against our quality rubric. This contractor role focuses on labeling edge cases, writing structured feedback, and helping retrain our models.

You will compare paired outputs, assign severity tags, and document recurring failure modes. Strong written reasoning and attention to detail are essential, with about 10 hours per week availability.

Qualifications

• Prior evaluation, annotation, or human-rater experience on browser automation task evaluation or adjacent content.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Reliable async availability for at least 10 hours per week.
• Excellent attention to detail and ability to flag when a prompt itself is the problem.

Responsibilities

• Evaluate browser automation task evaluation model outputs against a versioned rubric and assign severity tags for Browser Automation Task 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

Browser automation

Web research

Source grounding

Browser

Automation

Job description

AuraOne, Inc. is seeking a remote Browser Automation Task Evaluator to review prompts and responses against our quality rubric. This contractor role focuses on labeling edge cases, writing structured feedback, and helping retrain our models.

You will compare paired outputs, assign severity tags, and document recurring failure modes. Strong written reasoning and attention to detail are essential, with about 10 hours per week availability.