Remote Adversarial AI Security Engineer (AppSec)

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

Job summary

AI Trainer Jobs is seeking an Applications Security Engineer (AppSec) to work remotely on a red-team track that stress-tests AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and map each jailbreak to rubric clauses for patching.

You will design adversarial prompts, record reproducible steps, and score defenses across single-turn and multi-turn conversations. This is a contractor, remote-US eligible position with hourly compensation to be confirmed

Qualifications

• Experience red-teaming AI systems or adversarial ML research.
• Strong written reporting to document attack steps and remediation.
• Familiarity with prompt-injection, jailbreaks, and policy-bypass taxonomies.
• Ability to work asynchronously with at least 10 hours per week.

Responsibilities

• Design adversarial prompts that probe known weakness classes.
• Document every successful attack with reproduction steps and the policy clause violated.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route to the safety team with severity ratings.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

AppSec evaluation

Job description

AI Trainer Jobs is seeking an Applications Security Engineer (AppSec) to work remotely on a red-team track that stress-tests AI systems against adversarial prompts. Reviewers craft attack scenarios, document failure modes, and map each jailbreak to rubric clauses for patching.

You will design adversarial prompts, record reproducible steps, and score defenses across single-turn and multi-turn conversations. This is a contractor, remote-US eligible position with hourly compensation to be confirmed