Security Specialist (Remote)

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

We are hiring for one of our clients, seeking an AI Jailbreak & Prompt-Injection Security Expert to work on a Full-Time basis. The role focuses on identifying vulnerabilities in AI models, testing defenses against prompt-injection attacks, and developing robust security frameworks. Responsibilities include designing and executing jailbreak scenarios to assess model resilience.

Key Responsibilities

• Conduct deep-dive analysis of AI model vulnerabilities to prompt-injection and jailbreak techniques.
• Develop and refine testing methodologies to evaluate the robustness of AI security mechanisms.
• Document findings and recommend security improvements for AI systems.
• Collaborate with cross-functional teams to integrate security best practices into AI deployment pipelines.
• Stay current with emerging threats in AI security, including new jailbreak and injection vectors.

Required Skills & Qualifications

• Experience with AI security, prompt-injection, and jailbreak testing frameworks.
• Proficiency in Python and scripting for automated security testing.
• Knowledge of adversarial machine learning and ethical hacking techniques.
• Familiarity with AI model architectures and inference pipelines.
• Ability to analyze security logs and interpret model behavior under attack.
• Experience with threat modeling and risk assessment in AI systems.

More About the Opportunity

This role offers a unique opportunity to work with a global leader in the Technology, Information and Internet industry, contributing to the development of secure AI systems. The position involves direct impact on safeguarding AI deployments against evolving attack methods.

Equal Opportunity Employer

We hire based on skills and expertise. All qualified candidates are welcome regardless of background, experience, or prior employment history. Applications are reviewed solely on demonstrated technical ability and qualifications.