Remote AI Safety Red-Team Expert (Ukrainian)

AuraOne; United States; On-site; USD 52,000 - 58,000; Part time

Benefits offered by this job

Remote work

Job summary

AuraOne seeks a Bilingual Ukrainian Generalist Expert — AI Safety to remotely stress test AI systems by crafting adversarial prompts and documenting failures with reproducible steps. You’ll pair each jailbreak with its violated policy clause to help patch gaps.

You’ll score defenses in single- and multi-turn conversations, triage new attack vectors, and maintain a library of red-team rubrics while staying aligned with the broader safety team. This is a contractor, remote-to-US role.

Qualifications

• Experience red-teaming AI systems, security research, or adversarial ML work for Bilingual Ukrainian Generalist Expert — AI Safety assignments.
• Strong written communication — your reports become the patch ticket.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Bilingual Ukrainian Generalist Expert — 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 Ukrainian Generalist AI SAF

Job description

AuraOne seeks a Bilingual Ukrainian Generalist Expert — AI Safety to remotely stress test AI systems by crafting adversarial prompts and documenting failures with reproducible steps. You’ll pair each jailbreak with its violated policy clause to help patch gaps.

You’ll score defenses in single- and multi-turn conversations, triage new attack vectors, and maintain a library of red-team rubrics while staying aligned with the broader safety team. This is a contractor, remote-to-US role.