AI Security Expert for Jailbreak & Prompt Injection

Role Overview

Design and execute adversarial evaluations that probe and harden large language models and AI agents. In this contractor role you will create ethical jailbreaks, probe prompt-injection and tool-use abuse scenarios, and produce high-quality outputs used to train and improve next-generation AI systems. No prior AI employment is required, your domain expertise and security skills are the priority.

Key Responsibilities

• Design and implement methodologies for evaluating AI safety, focusing 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.
• Develop, maintain, and update regression test suites that systematically check for jailbreak susceptibility and prompt-injection vulnerabilities.
• Build evaluation frameworks that stress-test models against realistic adversarial threats to improve robustness.
• Collaborate with technical stakeholders to translate security findings into actionable model safety and risk mitigation recommendations.
• Document methodologies, results, and best practices in clear written reports and presentations for technical and non-technical audiences.

Qualifications

• Required skills: Ethical jailbreaks, LLM red teaming, prompt injection, tool-use abuse.
• Preferred: 2+ years of experience 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 such as MS or PhD in computer science, cybersecurity, machine learning, or a related field, or equivalent professional or operational experience.
• High credibility in the AI security or adversarial ML community is desirable, for example published research, open-source tools, or conference presentations.
• Exceptional written and verbal communication skills, with emphasis on clear documentation and collaborative problem solving.
• Familiarity with current LLM architectures, prompt engineering techniques, and security assessment tools is strongly preferred.
• Prior participation in multi-disciplinary or cross-functional AI safety initiatives is a plus.
• No prior professional AI experience is strictly required; relevant domain knowledge and security expertise are valued.

Work Terms

• Engagement type: Independent contractor.
• Location: Remote.
• Work contributes to a customer-facing initiative focused on AI safety and robustness, with outputs used to train and evaluate frontier models.

Compensation

Hourly rate: $50 - $90 per hour.

About the organization

The hiring organization is a leading AI data lab that converts domain expertise into training data, evaluations, and feedback loops to improve how AI systems learn, reason, and perform.