Remote Adversarial AI QA Reviewer

AuraOne, Inc.; United States; Remote; USD 55,000 - 110,000; Full time

Job summary

AuraOne, Inc. is seeking a remote Schema Alignment Ontology QA Reviewer to help stress-test AI systems by crafting adversarial prompts, documenting failures, and mapping each jailbreak to the violated policy clause.

The role emphasizes rigorous reproduction steps and clear patch tickets for the safety team. The ideal candidate has experience red-teaming AI systems and strong written communication, with comfort navigating policy-grey areas and documenting what was attempted and why.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Schema Alignment Ontology QA Reviewer role.
• Strong written communication — reports become the patch ticket.
• Comfort working in policy-grey areas with clear documentation of what was attempted and why.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Schema Alignment Ontology QA Reviewer assignments.
• Document every successful attack with reproduction steps and the policy clause it violated.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route them to the safety team with severity ratings.
• Maintain a personal library of attack patterns and propose new red-team rubrics.
• Calibrate against the broader red-team cohort to keep coverage and severity consistent.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Schema Alignment Ontology QA

Data quality

Taxonomy design

Ontology review

Schema

Alignment

Job description

AuraOne, Inc. is seeking a remote Schema Alignment Ontology QA Reviewer to help stress-test AI systems by crafting adversarial prompts, documenting failures, and mapping each jailbreak to the violated policy clause.

The role emphasizes rigorous reproduction steps and clear patch tickets for the safety team. The ideal candidate has experience red-teaming AI systems and strong written communication, with comfort navigating policy-grey areas and documenting what was attempted and why.