AI Security Analyst: Frontier Models (Remote)

Alignerr Corp.; Sydney; Remote; AUD 83,000 - 165,000; Full time

Job summary

Alignerr is seeking an AI Security Analyst to stress-test frontier models, probe vulnerabilities, and improve safety and reliability of advanced AI systems. The role is a fully remote, hourly contract designed for security professionals curious about AI at the intersection of two major tech frontiers.

You will analyze AI security scenarios, review prompt injection risks, data leakage patterns, and model misuse, and contribute to robust defense strategies with flexible scheduling.

Qualifications

• Background in cybersecurity or a related technical field.
• Knowledge of threat modeling for AI or emerging tech.
• Familiar with prompt injection, adversarial inputs, data poisoning.
• Analytical and rigorous approach to complex systems.
• Ability to work independently with discipline and curiosity.

Responsibilities

• Analyze AI and LLM security scenarios to see how models behave under adversarial conditions.
• Review prompt injection attacks, data leakage risks, model abuse patterns, and system misuse.
• Classify security issues by impact and likelihood, and recommend mitigations.
• Help evaluate and improve AI system behavior to be safe, aligned, and resilient.
• Work on realistic, hands-on frontier AI scenarios with autonomy.

Skills

Cybersecurity

Threat modeling

AI/ML security

Analytical mindset

Independent work

Ambiguity handling

Tools

MITRE ATT&CK

OWASP

Job description

Alignerr is seeking an AI Security Analyst to stress-test frontier models, probe vulnerabilities, and improve safety and reliability of advanced AI systems. The role is a fully remote, hourly contract designed for security professionals curious about AI at the intersection of two major tech frontiers.

You will analyze AI security scenarios, review prompt injection risks, data leakage patterns, and model misuse, and contribute to robust defense strategies with flexible scheduling.