AI Safety Red-Team Engineer (Remote)

AI Trainer Jobs; United States; Remote; USD 83,000 - 131,000; Part time

Job summary

AI Trainer Jobs is seeking an experienced contractor for an AI Safety and Red-Team Evaluator role. You will design adversarial prompts to probe AI systems, document failures with clear reproduction steps, and pair each jailbreak with the violated rubric clause to help patch gaps.

Ideal candidates bring red-teaming AI experience, strong written communication, and disciplined documentation of what was attempted and why.

Qualifications

• Red-teaming AI systems or adversarial ML experience.
• Strong written communication; reports become patch tickets.
• Ability to document what was attempted and why.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection).
• Document every successful attack with reproduction steps and the violated policy clause.
• 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.

Skills

Red-team experience

Security research

Adversarial ML

Adversarial prompting

Red-team analysis

Policy taxonomy

Written communication

Job description

AI Trainer Jobs is seeking an experienced contractor for an AI Safety and Red-Team Evaluator role. You will design adversarial prompts to probe AI systems, document failures with clear reproduction steps, and pair each jailbreak with the violated rubric clause to help patch gaps.

Ideal candidates bring red-teaming AI experience, strong written communication, and disciplined documentation of what was attempted and why.