Remote Social Engineering Evaluator & Rubric Specialist

AuraOne, Inc.; United States; Remote; USD 55,000 - 83,000; Full time

Job summary

AuraOne, Inc. is seeking a Social Engineering Security Evaluator for a remote evaluation track. You will review prompts and responses, compare paired outputs, and label edge cases using AuraOne's rubric. This is a contractor role with US eligibility.

You will document rationales, provide structured feedback for retraining, and help improve guardrails and detection of unsafe content. The work is asynchronous, requires strong written reasoning, and a commitment of about 10 hours per week.

Qualifications

• Prior evaluation, annotation, or human-rater experience on social engineering security 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.

Responsibilities

• Evaluate social engineering security evaluation model outputs against a versioned rubric and assign severity tags for Social Engineering Security 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 evaluation

Rubric annotation

Severity tagging

Inter-rater calibration

Social engineering evaluation

Security review

Adversarial testing

Threat modeling

Job description

AuraOne, Inc. is seeking a Social Engineering Security Evaluator for a remote evaluation track. You will review prompts and responses, compare paired outputs, and label edge cases using AuraOne's rubric. This is a contractor role with US eligibility.

You will document rationales, provide structured feedback for retraining, and help improve guardrails and detection of unsafe content. The work is asynchronous, requires strong written reasoning, and a commitment of about 10 hours per week.