Remote AI Safety Red Team Specialist (Adversarial Testing)

AI Trainer Jobs; United States; Remote; USD 90,000 - 96,000; Full time

Job summary

AI Trainer Jobs is seeking an Autonomous Replication Risk Red Team Specialist for a remote, US-eligible contractor role. You will design adversarial prompts, document failures, and map each jailbreak to the violated policy clause to help patch gaps.

You will score defenses across single-turn and multi-turn conversations, triage new attack vectors, and provide clear, reproducible reports to the safety team. The position offers hourly pay and remote work with flexible scheduling.

Qualifications

• Demonstrated experience red-teaming AI systems or adversarial ML work.
• Strong written communication; reports become patch tickets.
• Comfort with policy-grey areas and clear documentation.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Design adversarial prompts probing known weakness classes.
• Document every successful attack with reproduction steps and policy violated.
• Score defenses across single-turn and multi-turn conversations.
• Triage new attack vectors and route to safety team with severity.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Adversarial testing

AI safety

Red-team evaluation

Policy rubrics

Autonomous replication

Risk assessment

Job description

AI Trainer Jobs is seeking an Autonomous Replication Risk Red Team Specialist for a remote, US-eligible contractor role. You will design adversarial prompts, document failures, and map each jailbreak to the violated policy clause to help patch gaps.

You will score defenses across single-turn and multi-turn conversations, triage new attack vectors, and provide clear, reproducible reports to the safety team. The position offers hourly pay and remote work with flexible scheduling.