Remote AI Security Analyst - Threat Modeling & LLM Safety

Alignerr Corp.; Municipio de Rincón de los Sauces; Remote; ARS 104,413,000 - 208,825,000; Part time

Job summary

Alignerr is seeking AI Security Analysts to probe, evaluate, and stress-test cutting-edge AI models, identifying vulnerabilities before bad actors do and ensuring safety foundations. This is a fully remote hourly contract with 10–40 hours per week, offering flexible, task-based work.

You will analyze AI security scenarios, review prompt injection and data leakage cases, and propose mitigations based on impact. Ideal candidates blend cybersecurity with curiosity about AI safety.

Qualifications

• Background in cybersecurity, application security, or a closely related field.
• Solid understanding of modern threat modeling.
• Familiar with adversarial thinking and how it applies to AI systems.
• Analytical and precise when evaluating complex systems and failure modes.
• Clear written communicator who can document findings clearly.
• Self-motivated and reliable when working independently.

Responsibilities

• Analyze AI and LLM security scenarios to understand behavior under adversarial conditions.
• Review and evaluate cases involving prompt injection, data leakage, model abuse, and system misuse.
• Classify security issues and recommend mitigations based on impact and likelihood.
• Help evaluate and improve AI system behavior to stay safe and aligned with security practices.
• Work with realistic frontier AI development scenarios and deployments.
• Complete task-based assignments independently on your schedule.

Skills

Threat modeling

Adversarial thinking

Analytical thinking

Clear communicator

Independent work

Security mindset

Tools

AI APIs

Job description

Alignerr is seeking AI Security Analysts to probe, evaluate, and stress-test cutting-edge AI models, identifying vulnerabilities before bad actors do and ensuring safety foundations. This is a fully remote hourly contract with 10–40 hours per week, offering flexible, task-based work.

You will analyze AI security scenarios, review prompt injection and data leakage cases, and propose mitigations based on impact. Ideal candidates blend cybersecurity with curiosity about AI safety.