Remote AI Safety Red-Team Expert (Polish PhD)

AuraOne, Inc.; United States; Remote; USD 69,000 - 74,000; Part time

Job summary

AuraOne, Inc. is seeking a Bilingual Polish STEM Expert (PhD) for a remote AI Safety red-team track. You will design adversarial prompts, document failures with rigorous reproduction steps, and map each attack to the violated rubric clause to guide patches.

Responsibilities include scoring defenses in both single-turn and multi-turn conversations, triaging new attack vectors, and maintaining a catalog of red-team rubrics to ensure consistent coverage and severity ratings across the team.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication and 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

Polish generalist evaluation

Education

PhD in STEM

Job description

AuraOne, Inc. is seeking a Bilingual Polish STEM Expert (PhD) for a remote AI Safety red-team track. You will design adversarial prompts, document failures with rigorous reproduction steps, and map each attack to the violated rubric clause to guide patches.

Responsibilities include scoring defenses in both single-turn and multi-turn conversations, triaging new attack vectors, and maintaining a catalog of red-team rubrics to ensure consistent coverage and severity ratings across the team.