Remote AI Security Analyst: Adversarial Testing

Alignerr Corp.; Greater London; Teletrabalho; GBP 55 000 - 165 000; Tempo parcial

Resumo da oferta

Alignerr is seeking security-minded professionals to probe, stress-test, and red-team AI models, uncovering weaknesses before they become real-world problems. This is a remote, flexible hourly contract role where your cybersecurity expertise translates into meaningful impact on AI safety used worldwide.

You'll conduct red-teaming exercises, design adversarial prompts, and document vulnerabilities in clear reports, collaborating with engineering to implement practical mitigations and stay current

Qualificações

• Solid grounding in cybersecurity concepts — threat modeling, penetration testing, or vulnerability research.
• Hands-on experience with AI/ML systems, LLMs, or prompt engineering.
• A creative, adversarial mindset — you love finding the cracks in things to make them stronger.
• Strong written communication skills for clear, actionable reporting.

Responsabilidades

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

Conhecimentos

Threat modeling

Penetration testing

Vulnerability research

AI/ML systems

LLMs

Prompt engineering

Adversarial mindset

Written communication

Self-directed work

Open-source AI platforms

Descrição da oferta de emprego

Alignerr is seeking security-minded professionals to probe, stress-test, and red-team AI models, uncovering weaknesses before they become real-world problems. This is a remote, flexible hourly contract role where your cybersecurity expertise translates into meaningful impact on AI safety used worldwide.

You'll conduct red-teaming exercises, design adversarial prompts, and document vulnerabilities in clear reports, collaborating with engineering to implement practical mitigations and stay current