Remote AI Security Analyst: Frontier Models & Threats

Alignerr; France; Sur place; EUR 83 000 - 152 000; Temps partiel

Résumé du poste

Alignerr is seeking AI Security Analysts to stress-test frontier models, probing vulnerabilities and adversarial scenarios to keep AI safe and reliable.

This is a fully remote hourly contract, 10–40 hours per week, offering flexible scheduling for security professionals eager to learn how AI systems are built, attacked, and defended.

Join Alignerr to work independently on meaningful tasks, with opportunities for ongoing projects as new deployments arise.

Qualifications

• Background in cybersecurity or information security.
• Understanding of threat modeling for AI/LLM systems.
• Familiar with adversarial attack surfaces such as prompt injection and data leakage.
• Analytical and precise when dissecting complex systems.
• Self-motivated and able to work independently.

Responsabilités

• Analyze AI and LLM security scenarios under adversarial conditions.
• Investigate prompt injection attacks and data leakage risks.
• Classify vulnerabilities and recommend mitigations based on impact and likelihood.
• Apply threat modeling frameworks to emerging AI technologies and deployments.
• Evaluate and improve AI system behavior to align with security best practices.
• Work independently on task-based assignments at your own pace.

Connaissances

Cybersecurity background

Threat modeling

AI/LLM security

Analytical mindset

Independent work

Description du poste

Alignerr is seeking AI Security Analysts to stress-test frontier models, probing vulnerabilities and adversarial scenarios to keep AI safe and reliable.

This is a fully remote hourly contract, 10–40 hours per week, offering flexible scheduling for security professionals eager to learn how AI systems are built, attacked, and defended.

Join Alignerr to work independently on meaningful tasks, with opportunities for ongoing projects as new deployments arise.