AI Jailbreak & Prompt-Injection Security Specialist Remote

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

Job summary

AI Trainer Jobs is seeking a remote contractor to perform AI Jailbreak & Prompt-Injection Security testing. The role focuses on adversarial prompts, documentation, and evaluation of defenses across both single-turn and multi-turn interactions.

The work is remote with US eligibility, paid hourly, and placement depends on program demand. Candidates should bring offensive security or adversarial ML experience and strong reporting skills.

Qualifications

• Experience red-teaming AI systems, security research, or adversarial ML work.
• Strong written communication; reports become patch tickets.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for AI Jailbreak & Prompt-Injection Security Expert 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

Jailbreak evaluation

AI model evaluation

Job description

AI Trainer Jobs is seeking a remote contractor to perform AI Jailbreak & Prompt-Injection Security testing. The role focuses on adversarial prompts, documentation, and evaluation of defenses across both single-turn and multi-turn interactions.

The work is remote with US eligibility, paid hourly, and placement depends on program demand. Candidates should bring offensive security or adversarial ML experience and strong reporting skills.