Polish-English AI Safety Red Team Expert (PhD)

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

Job summary

AuraOne is seeking a Bilingual Polish STEM Expert (PhD) for a remote AI Safety red-team role. You will design adversarial prompts, document failures with precise reproduction steps, and rate defenses across turn-based conversations to harden AI models before release.

Remote work is supported with US eligibility; contractor placement with program-defined task volume and review pacing. Strong documentation, multilingual capability, and policy-awareness are essential to succeed in this role.

Qualifications

• Multilingual fluency for cross-language attack testing.
• Experience in offensive security, AppSec, or adversarial ML is a plus.
• Ability to document complex attack scenarios clearly for patching

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.
• Triaged emerging attack vectors and routed them to the safety team with severity ratings.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Polish generalist evaluation

Job description

AuraOne is seeking a Bilingual Polish STEM Expert (PhD) for a remote AI Safety red-team role. You will design adversarial prompts, document failures with precise reproduction steps, and rate defenses across turn-based conversations to harden AI models before release.

Remote work is supported with US eligibility; contractor placement with program-defined task volume and review pacing. Strong documentation, multilingual capability, and policy-awareness are essential to succeed in this role.