AI Security Tester — Remote Red-Teaming & Guardrails

Alignerr Corp.; Sydney; Remote; AUD 83,000 - 152,000; Part time

Benefits offered by this job

Fully remote

Job summary

Alignerr Corp. is hiring security-minded professionals to red-team AI models, probe safety guardrails, and help make the next generation of AI systems more robust and trustworthy.

This is a fully remote, flexible hourly contract role where your work directly shapes the safety of AI products used by millions of people. You will conduct red-teaming, design adversarial prompts, evaluate outputs for safety, document findings, and collaborate with engineers to implement mitigations, while staying

Qualifications

• Solid understanding of cybersecurity concepts.
• Experience with threat modeling or penetration testing.
• Hands-on with AI/ML systems, LLMs, or prompt engineering.

Responsibilities

• 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.

Skills

Cybersecurity

Threat modeling

Penetration testing

AI/ML systems

LLMs

Prompt engineering

Tools

Open-source AI platforms

Job description

Alignerr Corp. is hiring security-minded professionals to red-team AI models, probe safety guardrails, and help make the next generation of AI systems more robust and trustworthy.

This is a fully remote, flexible hourly contract role where your work directly shapes the safety of AI products used by millions of people. You will conduct red-teaming, design adversarial prompts, evaluate outputs for safety, document findings, and collaborate with engineers to implement mitigations, while staying