Remote AI Prompt Injection Security Tester

AI Trainer Jobs; United States; Remote; USD 96,000 - 138,000; Full time

Job summary

AuraOne is seeking a remote contractor to conduct adversarial evaluation of AI systems, focusing on prompt injection and safety gaps. You will design jailbreaks, document failures with precision, and rate defenses across single-turn and multi-turn conversations to help harden models before deployment.

Ideal candidates have a security research background, strong reporting skills, and the ability to work asynchronously for at least 10 hours per week.

Qualifications

• Background in offensive security, AppSec, or trust & safety operations.
• Experience publishing or reproducing public adversarial-ML research.
• Multilingual fluency for cross-language attack testing.

Responsibilities

• Design adversarial prompts to probe known weakness classes for Prompt Injection Security Evaluator 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

Prompt Injection Security evaluation

Security review

Adversarial testing

Threat modeling

Clear reporting

Job description

AuraOne is seeking a remote contractor to conduct adversarial evaluation of AI systems, focusing on prompt injection and safety gaps. You will design jailbreaks, document failures with precision, and rate defenses across single-turn and multi-turn conversations to help harden models before deployment.

Ideal candidates have a security research background, strong reporting skills, and the ability to work asynchronously for at least 10 hours per week.