Adversarial AI Security Engineer for ASIC/SoC (Remote)

AuraOne; United States; Remote; USD 96,000 - 138,000; Part time

Job summary

AI Trainer Jobs is seeking a remote ASIC/SoC Design & Verification Adversarial Engineer on a contractor basis to stress-test AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and pair each jailbreak with the rubric clause it violated so the safety team can patch the gap.

You will design adversarial prompts, score model defenses across single-turn and multi-turn conversations, triage new attack vectors, and report findings with rigorous reproduction

Qualifications

• Experience red-teaming AI systems and security research or adversarial ML.
• Strong written communication for patch tickets and reports.
• Ability to document attempted actions with clear rationale.

Responsibilities

• Design adversarial prompts that probe weakness classes for ASIC/SoC verification.
• Document successful attacks with reproduction steps and violated policy clause.
• Score defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route them to the safety team.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Documentation

Job description

AI Trainer Jobs is seeking a remote ASIC/SoC Design & Verification Adversarial Engineer on a contractor basis to stress-test AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and pair each jailbreak with the rubric clause it violated so the safety team can patch the gap.

You will design adversarial prompts, score model defenses across single-turn and multi-turn conversations, triage new attack vectors, and report findings with rigorous reproduction