Job Opportunities API

Role Overview Help harden next-generation AI systems by designing and executing evaluations that expose jailbreaks, prompt-injection attacks, and tool-use abuse. In this contractor role you will create adversarial test strategies and regression suites, surface realistic multi-turn bypass patterns, and translate discoveries into concrete recommendations that improve model safety and robustness. No prior AI experience is required, your domain expertise and security skills are what matter. Key Responsibilities • Design and implement advanced evaluation methodologies focused on ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse scenarios. • Create cross-domain elicitation strategies to reveal multi-turn and complex adversarial bypass patterns in models. • Develop, maintain, and update regression test suites that systematically test for jailbreak susceptibility and prompt-injection vulnerabilities. • Build evaluation frameworks that stress-test models against real-world adversarial threats to improve overall system robustness. • Collaborate with technical stakeholders to translate security findings into actionable model safety and risk mitigation steps. • Document methodologies, results, and best practices in clear written reports and presentations for both technical and non-technical audiences. Qualifications • Required skills include ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse testing. • Preferred: 2 or more years of experience in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security field. • Proven track record researching, testing, or uncovering vulnerabilities related to 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 experience. • High credibility within the AI security or adversarial ML community, for example published research, open-source tooling, or conference presentations. • Exceptional written and verbal communication skills, with an emphasis on clear documentation and collaborative problem solving. • Familiarity with current LLM architectures, prompt engineering techniques, and security assessment tools is highly desirable. Prior participation in multi-disciplinary or cross-functional AI safety projects is a plus. Work Terms • Role type, contractor. • Location, remote. • No prior AI employment required, domain expertise is accepted in lieu of prior AI work. Compensation Pay range, $50 - $90 per hour. About the Organization The organization operates as an AI data lab that transforms real-world subject matter expertise into training data, evaluations, and feedback loops to improve how AI systems learn, reason, and perform. Experts contribute across domains such as finance, healthcare, and STEM engineering, and the network is built to scale high-quality expert input into frontier model development. How to Apply If you are interested, follow the application instructions on this posting to express interest and provide any requested information.