Remote AI Security Tester - Red-Team & Safeguards

Alignerr Corp.; Sydney; À distance; AUD 83 000 - 165 000; Temps partiel

Résumé du poste

Alignerr is hiring security-minded professionals to red-team AI models, probe safety guardrails, and help make AI systems more robust and trustworthy. This is a fully remote, flexible contract role where your work directly shapes the safety of AI products used by millions.

As part of the role, you will conduct red-teaming exercises to uncover security weaknesses, design adversarial prompts, evaluate outputs for safety and bias, and document vulnerabilities in clear reports.

Qualifications

• Solid understanding of cybersecurity concepts and threat modeling.

Responsabilités

• Conduct red-teaming exercises to uncover security weaknesses in AI systems.
• Design and execute adversarial prompts and edge-case scenarios to stress-test model guardrails.
• Evaluate AI outputs for safety risks, bias, and policy compliance.
• Document vulnerabilities, unexpected behaviors, and exploits in clear, structured reports.
• Collaborate with engineering teams to recommend practical mitigations and improvements.
• Stay current on emerging AI security threats, jailbreak techniques, and evolving best practices.
• Help define and refine security evaluation rubrics and testing protocols.

Connaissances

Cybersecurity concepts

Threat modeling

Penetration testing

AI/ML security

Description du poste

Alignerr is hiring security-minded professionals to red-team AI models, probe safety guardrails, and help make AI systems more robust and trustworthy. This is a fully remote, flexible contract role where your work directly shapes the safety of AI products used by millions.

As part of the role, you will conduct red-teaming exercises to uncover security weaknesses, design adversarial prompts, evaluate outputs for safety and bias, and document vulnerabilities in clear reports.