AI Jailbreak & Prompt-Injection Security Expert

What You'll Do6

• Design and implement advanced methods for evaluating AI system safety, with emphasis on ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse.
• Create cross-domain elicitation strategies to uncover multi-turn and complex adversarial bypass patterns in AI models.
• Develop, maintain, and update regression test suites that systematically test for jailbreak susceptibility and prompt-injection vulnerabilities.
• Construct evaluation frameworks that stress-test AI models against real-world adversarial threats to enhance system robustness.
• Collaborate with technical stakeholders to translate security findings into actionable improvements for model safety and risk mitigation.
• Document methodologies, findings, and best practices in clear written reports and presentations for technical and non-technical audiences.

Requirements7

• 2+ years of expertise in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security domain.
• Proven experience researching, testing, or uncovering vulnerabilities related to ethical jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
• Advanced degree (PhD, MS) in computer science, cybersecurity, machine learning, or a relevant discipline, or equivalent operational/professional background.
• High credibility and recognition within the AI security or adversarial ML community, such as published research, open-source tools, or conference presentations.
• Exceptional written and verbal communication skills, with a strong focus on clear documentation and collaborative problem-solving.
• Prior participation in multi-disciplinary projects or cross-functional AI safety initiatives is a plus.
• Familiarity with current LLM architectures, prompt engineering techniques, and security assessment tools is highly desirable.

Who Should Apply

The ideal candidate has hands-on experience in adversarial ML or LLM red teaming, with a track record of uncovering jailbreak or prompt-injection vulnerabilities. You hold an advanced degree or equivalent experience and have contributed to the AI security community through research, tools, or talks. Strong documentation and communication skills are essential.

Salary Insight