Remote Harmful Instruction Risk Evaluator

AuraOne; United States; On-site; USD 82,656 - 165,312; Full time

Job summary

AuraOne is seeking a remote Harmful Instruction Refusal Risk Evaluator to stress-test AI systems through adversarial prompts and rigorous documentation. You will craft attack scenarios, record failures with exact steps, and map each breach to the violated policy clause to help patch gaps before release.

The role emphasizes strong written reporting, clear rationale for each attempt, and the ability to work asynchronously for at least 10 hours per week from a US-based remote setup.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Harmful Instruction Refusal Risk Evaluator work.
• Strong written communication so reports become patch tickets.
• Clear documentation of what was attempted and why.

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.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Harmful Instruction Refusal Risk eval

AI safety

Red-team evaluation

Policy rubrics

Harmful

Instruction

Refusal

Job description

AuraOne is seeking a remote Harmful Instruction Refusal Risk Evaluator to stress-test AI systems through adversarial prompts and rigorous documentation. You will craft attack scenarios, record failures with exact steps, and map each breach to the violated policy clause to help patch gaps before release.

The role emphasizes strong written reporting, clear rationale for each attempt, and the ability to work asynchronously for at least 10 hours per week from a US-based remote setup.