AI Safety Practitioner

AuraOne; United States; On-site; USD 83,000 - 96,000; Part time

Job summary

AI Trainer Jobs seeks an AI Safety Practitioner for remote engagement as a contractor. You will craft adversarial prompts to test AI systems, document failures with rigorous reproduction steps, and map each jailbreak to the violated policy clause for patching gaps.

Responsibilities include scoring defenses across turns, triaging new attack vectors with severity, and maintaining libraries of attack patterns to evolve red-team rubrics.

Qualifications

• Experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication: reports become patch tickets.
• Comfort documenting reasoning in policy-grey areas with clear justification.

Responsibilities

• Design adversarial prompts that probe known weakness classes.
• Document every successful attack with reproduction steps and policy clause violated.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route to safety team with severity ratings.
• Maintain a personal library of attack patterns and propose new rubrics.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

AI Safety Practitioner evaluation

Job description

About the role

AI Safety Practitioner 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.
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.
Push on refusal boundaries and dual-use risk before a model ships.

Responsibilities

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

What you should bring

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for AI Safety Practitioner 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.

Role signals

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.

Useful experience

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

Compensation and schedule

$60-$70 / hr
Expected arrangement: contractor , with program-defined task volume and review pacing. Placement depends on current program demand and reviewer confirmation.

Skills used in matching

• Adversarial prompting
• Red-team analysis
• Policy taxonomy
• Failure documentation
• AI Safety Practitioner evaluation