AI Safety Red-Teamer — Remote

Alignerr Corp.; Sydney; Remote; AUD 96,000 - 179,000; Part time

Benefits offered by this job

Fully remote

Flexible schedule

Job summary

Alignerr Corp. is seeking security-minded professionals to red-team AI models, probe safety guardrails, and help strengthen AI systems. This fully remote hourly contract allows 10–40 hours per week with flexible scheduling and global collaboration.

You will conduct red-teaming, craft adversarial prompts, evaluate outputs for safety and bias, and document findings for engineering teams to mitigate risks. Independent, precise work is essential.

Qualifications

• Solid understanding of cybersecurity concepts, threat modeling, or penetration testing.
• Hands-on with AI/ML systems, LLMs, or prompt engineering.
• Creative, analytical thinker who enjoys breaking things to improve.
• Clear writing and precise documentation of findings.
• Ability to work independently on asynchronous, task-based assignments.
• Familiarity with open-source AI platforms is a plus.
• Background in infosec, ethical hacking, or AI safety research is a bonus.

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

Threat modeling

Penetration testing

AI/ML systems

LLMs

Prompt engineering

Analytical thinking

Technical writing

Independent work

Open-source AI

Infosec / Ethical hacking

AI safety

Tools

Open-source platforms

Job description

Alignerr Corp. is seeking security-minded professionals to red-team AI models, probe safety guardrails, and help strengthen AI systems. This fully remote hourly contract allows 10–40 hours per week with flexible scheduling and global collaboration.

You will conduct red-teaming, craft adversarial prompts, evaluate outputs for safety and bias, and document findings for engineering teams to mitigate risks. Independent, precise work is essential.