Remote AI Security Analyst: Threat Modeling & Safety

Alignerr Corp.; City of Melbourne; Remoto; AUD 83.000 - 138.000; Part-time

Descrizione del lavoro

Alignerr is seeking an AI Security Analyst to probe frontier models and assess threat scenarios, ensuring safety and resilience of cutting-edge AI systems. This is a remote, hourly contract role for security professionals curious about AI and ready to work at the edge of technology and risk.

You'll analyze AI and LLM security scenarios, review prompt injection, data leakage, model abuse, and system misuse, and provide actionable mitigations and feedback to improve safety and alignment.

Competenze

• Background in cybersecurity, information security, or a related technical field.
• Strong understanding of threat modeling, attack surfaces, and adversarial thinking.
• Curiously about how AI systems are built, deployed, and exploited.
• Analytical and precise thinking, focusing on edge cases and failure modes.
• Able to articulate risk assessments clearly in writing.
• Self-motivated and reliable when working independently.

Mansioni

• Analyze AI and LLM security scenarios to understand model behavior under adversarial or unexpected conditions.
• Review and assess cases involving prompt injection, data leakage, model abuse, and system misuse.
• Classify security vulnerabilities and recommend mitigations based on impact and likelihood.
• Apply security threat modeling frameworks to emerging AI technologies.
• Evaluate AI system behavior and provide structured feedback to improve safety and alignment.
• Work independently and asynchronously on your own schedule.

Conoscenze

Cybersecurity

Threat modeling

Adversarial thinking

Technical writing

Independent work

Descrizione del lavoro

Alignerr is seeking an AI Security Analyst to probe frontier models and assess threat scenarios, ensuring safety and resilience of cutting-edge AI systems. This is a remote, hourly contract role for security professionals curious about AI and ready to work at the edge of technology and risk.

You'll analyze AI and LLM security scenarios, review prompt injection, data leakage, model abuse, and system misuse, and provide actionable mitigations and feedback to improve safety and alignment.