AI Security Engineer: Prompt-Injection & Jailbreak Defense

Hired; France; Sur place; EUR 90 000 - 130 000; Plein temps

Résumé du poste

Hired is seeking an AI Jailbreak & Prompt-Injection Security Expert on a full-time basis to identify vulnerabilities in AI models, test defenses against prompt-injection attacks, and design robust security frameworks.

The role involves designing and executing jailbreak scenarios, refining testing methodologies, and collaborating with cross-functional teams to integrate security best practices into AI deployment pipelines.

Qualifications

• Experience in AI security and jailbreak testing.
• Proficient in Python for automated security testing.
• Knowledge of adversarial ML and ethical hacking practices.

Responsabilités

• Conduct deep-dive analyses of AI model vulnerabilities to prompt-injection and jailbreak techniques.
• Develop and refine testing methodologies to evaluate AI security robustness.
• Document findings and recommend security improvements for AI systems.

Connaissances

AI security

prompt-injection

jailbreak testing

Python

adversarial ML

threat modeling

Description du poste

Hired is seeking an AI Jailbreak & Prompt-Injection Security Expert on a full-time basis to identify vulnerabilities in AI models, test defenses against prompt-injection attacks, and design robust security frameworks.

The role involves designing and executing jailbreak scenarios, refining testing methodologies, and collaborating with cross-functional teams to integrate security best practices into AI deployment pipelines.