Remote Dutch AI Safety Red-Team Scientist (PhD)

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

Job summary

AuraOne is seeking a Bilingual Dutch (Netherlands) STEM Expert (PhD) for AI Safety. This remote contractor role focuses on adversarial evaluation, stress-testing AI systems, and documenting failure modes with rigorous patch tickets.

You will design jailbreak prompts, score defenses in single- and multi-turn conversations, triage new attack vectors, and maintain a library of attack patterns. Strong written communication and experience red-teaming AI are essential; remote US eligibility applies

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML 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.

Responsibilities

• Design adversarial prompts that probe known weakness classes for AI Safety 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

Bilingual Dutch STEM AI Safety

Job description

AuraOne is seeking a Bilingual Dutch (Netherlands) STEM Expert (PhD) for AI Safety. This remote contractor role focuses on adversarial evaluation, stress-testing AI systems, and documenting failure modes with rigorous patch tickets.

You will design jailbreak prompts, score defenses in single- and multi-turn conversations, triage new attack vectors, and maintain a library of attack patterns. Strong written communication and experience red-teaming AI are essential; remote US eligibility applies