Remote AI Safety Red-Team Researcher (Dutch STEM PhD)

AuraOne; United States; Remote; USD 84,000 - 90,000; Full time

Job summary

AuraOne is seeking a Bilingual Dutch (Belgium) STEM Expert (PhD) to work remotely as a contractor on AI Safety red-teaming. You will craft adversarial prompts, document failures, and pair each jailbreak with the violated rubric clause so the safety team can patch gaps.

Reviewers must think like attackers, reproduce failures, and write up patches for regression testing. This role is remote, US-eligible, with competitive hourly pay.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for a Bilingual Dutch (Belgium) STEM Expert (PhD) — AI Safety role.
• Ability to craft adversarial prompts and document failures with rigor for patching gaps.
• Familiarity with safety policy taxonomy and evidence-based patching.

Responsibilities

• Design adversarial prompts that probe known weakness classes for AI Safety assignments.
• Document every successful attack with reproduction steps and violated policy clause.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route them to the safety team with severity ratings.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Bilingual Dutch STEM AI Safety

Education

PhD

Job description

AuraOne is seeking a Bilingual Dutch (Belgium) STEM Expert (PhD) to work remotely as a contractor on AI Safety red-teaming. You will craft adversarial prompts, document failures, and pair each jailbreak with the violated rubric clause so the safety team can patch gaps.

Reviewers must think like attackers, reproduce failures, and write up patches for regression testing. This role is remote, US-eligible, with competitive hourly pay.