AI Safety Red-Team Evaluator - Harmful Instruction Refusal

AuraOne, Inc.; United States; Remote; USD 83,000 - 165,000; Part time

Benefits offered by this job

Background in offensive security

Public adversarial-ML research

Multilingual fluency for testing

Job summary

AuraOne, Inc. is seeking a Harmful Instruction Refusal Risk Evaluator as a remote contractor to stress-test AI systems against adversarial prompts.

You will design attack scenarios, document failures with rigor, and pair each successful jailbreak with the violated rubric clause so the safety team can patch the gap. Responsibilities include scoring defenses in single- and multi-turn conversations, triaging new attack vectors, and maintaining a library of attack patterns for ongoing rubric

Qualifications

• Red-teaming AI systems, security research, or adversarial ML work.
• 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 for Harmful Instruction Refusal Risk Evaluator 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

Red-team analysis

Security research

Adversarial ML

Written communication

Policy-grey work

Async availability

Job description

AuraOne, Inc. is seeking a Harmful Instruction Refusal Risk Evaluator as a remote contractor to stress-test AI systems against adversarial prompts.

You will design attack scenarios, document failures with rigor, and pair each successful jailbreak with the violated rubric clause so the safety team can patch the gap. Responsibilities include scoring defenses in single- and multi-turn conversations, triaging new attack vectors, and maintaining a library of attack patterns for ongoing rubric