AI Jailbreak & Prompt-Injection Security Expert [Remote]

Role Overview

Help strengthen next-generation AI systems by applying security expertise to identify, evaluate, and mitigate jailbreak, prompt-injection, and tool-use abuse risks. This remote contractor role focuses on producing high-quality, real-world safety evaluations that improve how AI models learn, reason, and perform.

Key Responsibilities

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

Qualifications

• 2+ years of experience in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security field.
• Experience researching, testing, or uncovering vulnerabilities involving ethical jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
• Strong knowledge of ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse.
• An advanced degree, such as a PhD or MS, in computer science, cybersecurity, machine learning, or a related discipline, or equivalent professional or operational experience.
• Credibility within the AI security or adversarial ML community, such as published research, open-source tools, or conference presentations.
• Excellent written and verbal communication skills, with an emphasis on clear documentation and collaborative problem-solving.
• Experience with multidisciplinary 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.

Work Terms

• Remote independent contractor engagement.
• No prior AI-industry experience is required, relevant domain expertise is valued.

Compensation

$50 to $90 per hour.