AI Security Tester
About The Role
If you've ever looked at a system and instinctively started thinking about how to break it, this role was made for you. We're looking for security-minded professionals to help stress-test and harden AI systems by finding vulnerabilities before bad actors do.
You'll conduct red-team exercises, craft adversarial prompts, and deliver expert feedback that directly shapes the safety and reliability of AI products used by millions of people worldwide.
ā¢ Organization: Alignerr
ā¢ Type: Hourly Contract
ā¢ Location: Remote
ā¢ Commitment: 10ā40 hours/week
What You'll Do
ā¢ Conduct red-teaming exercises to identify security weaknesses and failure modes in AI systems
ā¢ Craft adversarial prompts and edge-case scenarios designed to probe and stress-test model guardrails
ā¢ Evaluate AI outputs for safety risks, bias, and policy compliance
ā¢ Document vulnerabilities, exploits, and unexpected behaviors in clear, structured reports
ā¢ Collaborate with engineering teams to recommend practical mitigations and improvements
ā¢ Stay current on emerging AI security threats, jailbreak techniques, and evolving best practices
ā¢ Help define and refine security evaluation rubrics and testing protocols
Who You Are
ā¢ You have a solid understanding of cybersecurity concepts, threat modeling, or penetration testing
ā¢ You've worked hands-on with AI/ML systems, large language models, or prompt engineering
ā¢ You're a creative, analytical thinker who enjoys finding cracks in complex systems
ā¢ You write clearly and document findings in an organized, structured way
ā¢ You're comfortable working independently on task-based, asynchronous assignments
ā¢ Familiarity with open-source AI platforms is a plus
ā¢ A background in infosec, ethical hacking, or AI safety research is a bonus ā but not required
Why Join Us
ā¢ Work at the frontier of AI security alongside top research labs
ā¢ Directly influence the safety and robustness of AI systems at scale
ā¢ Full autonomy and a flexible schedule ā work when and how you want
ā¢ Build highly sought-after expertise in one of the fastest-growing fields in tech
ā¢ Potential for ongoing work, expanded scope, and long-term contract extension
ā¢ Be part of a global, collaborative community of experts shaping the future of AI
Apply tot his job
Apply To this Job
If you've ever looked at a system and instinctively started thinking about how to break it, this role was made for you. We're looking for security-minded professionals to help stress-test and harden AI systems by finding vulnerabilities before bad actors do.
You'll conduct red-team exercises, craft adversarial prompts, and deliver expert feedback that directly shapes the safety and reliability of AI products used by millions of people worldwide.
ā¢ Organization: Alignerr
ā¢ Type: Hourly Contract
ā¢ Location: Remote
ā¢ Commitment: 10ā40 hours/week
What You'll Do
ā¢ Conduct red-teaming exercises to identify security weaknesses and failure modes in AI systems
ā¢ Craft adversarial prompts and edge-case scenarios designed to probe and stress-test model guardrails
ā¢ Evaluate AI outputs for safety risks, bias, and policy compliance
ā¢ Document vulnerabilities, exploits, and unexpected behaviors in clear, structured reports
ā¢ Collaborate with engineering teams to recommend practical mitigations and improvements
ā¢ Stay current on emerging AI security threats, jailbreak techniques, and evolving best practices
ā¢ Help define and refine security evaluation rubrics and testing protocols
Who You Are
ā¢ You have a solid understanding of cybersecurity concepts, threat modeling, or penetration testing
ā¢ You've worked hands-on with AI/ML systems, large language models, or prompt engineering
ā¢ You're a creative, analytical thinker who enjoys finding cracks in complex systems
ā¢ You write clearly and document findings in an organized, structured way
ā¢ You're comfortable working independently on task-based, asynchronous assignments
ā¢ Familiarity with open-source AI platforms is a plus
ā¢ A background in infosec, ethical hacking, or AI safety research is a bonus ā but not required
Why Join Us
ā¢ Work at the frontier of AI security alongside top research labs
ā¢ Directly influence the safety and robustness of AI systems at scale
ā¢ Full autonomy and a flexible schedule ā work when and how you want
ā¢ Build highly sought-after expertise in one of the fastest-growing fields in tech
ā¢ Potential for ongoing work, expanded scope, and long-term contract extension
ā¢ Be part of a global, collaborative community of experts shaping the future of AI
Apply tot his job
Apply To this Job