Remote German AI Safety Red-Team Expert (PhD)

AuraOne; United States; Remote; USD 80,000 - 85,000; Part time

Benefits offered by this job

Remote work

Independent contractor

Job summary

AuraOne is seeking a Bilingual German STEM Expert (PhD) for a remote AI Safety role focused on adversarial evaluation. You will design prompts, document failures with reproducible steps, and score defenses across conversations to harden models before release.

Work as a contractor, with an emphasis on rigorous reporting and patching policy gaps. Multilingual testing is valued, with flexible remote scheduling and program-defined task volume.

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.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Bilingual German STEM Expert (PhD) — 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.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

German generalist evaluation

Education

PhD in STEM

Job description

AuraOne is seeking a Bilingual German STEM Expert (PhD) for a remote AI Safety role focused on adversarial evaluation. You will design prompts, document failures with reproducible steps, and score defenses across conversations to harden models before release.

Work as a contractor, with an emphasis on rigorous reporting and patching policy gaps. Multilingual testing is valued, with flexible remote scheduling and program-defined task volume.