Remote AI Security Tester & Red-Teaming Specialist

Alignerr Corp.; Sydney; On-site; AUD 96,000 - 165,000; Part time

Job summary

Alignerr Corp. is seeking security-minded professionals to red-team AI models and probe safety guardrails. This fully remote, hourly contract role offers flexible hours (10–40 hours/week) and a chance to influence the safety of AI products used by millions.

You will conduct red-teaming exercises, design adversarial prompts, and evaluate outputs for safety and bias. Collaboration with engineers will drive practical mitigations and evolving testing protocols.

Qualifications

• Solid understanding of cybersecurity concepts, threat modeling, or penetration testing.
• Experience with AI/ML systems, LLMs, or prompt engineering.
• Clear, precise documentation of findings and reports.
• Ability to work independently in async, task-based assignments.

Responsibilities

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

Skills

Cybersecurity concepts

Threat modeling

Penetration testing

AI/ML systems

Prompt engineering

Tools

Open-source AI platforms

Job description

Alignerr Corp. is seeking security-minded professionals to red-team AI models and probe safety guardrails. This fully remote, hourly contract role offers flexible hours (10–40 hours/week) and a chance to influence the safety of AI products used by millions.

You will conduct red-teaming exercises, design adversarial prompts, and evaluate outputs for safety and bias. Collaboration with engineers will drive practical mitigations and evolving testing protocols.