Harmful Instruction Refusal Risk Evaluator

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

Harmful Instruction Refusal Risk Evaluator is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the gap.

Why this role matters

Adversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers and write up failures with enough rigor that the modeling team can reproduce, fix, and regress-test them.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) 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.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Harmful Instruction Refusal Risk Evaluator work.
• Strong written communication — your 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.

Example tasks

• Construct a 5-turn adversarial conversation that bypasses a specific policy clause and write up the patch ticket.
• Score a model's defenses against a known jailbreak pattern across 20 variants.
• Propose a new red-team rubric category after spotting an emerging attack vector.
• Reproduce a failure another reviewer reported and confirm the severity tag.

Nice to have

• Background in offensive security, AppSec, or trust & safety operations.
• Experience publishing or reproducing public adversarial-ML research.
• Multilingual fluency for cross-language attack testing.

Skills

• Adversarial prompting
• Red-team analysis
• Policy taxonomy
• Failure documentation
• Harmful Instruction Refusal Risk evaluation
• AI safety
• Red-team evaluation
• Policy rubrics
• Harmful
• Instruction
• Refusal

Work model

Remote — US-eligible. Remote Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.

Compensation

Hourly rate confirmed after the interview process.