Remote AI Security Analyst — Frontier Models

Alignerr Corp.; Madrid; Remote; EUR 83,000 - 152,000; Full time

Job summary

Alignerr is seeking an AI Security Analyst to probe frontier AI models for vulnerabilities under adversarial conditions, helping ensure safety, reliability, and alignment with security standards.

This is a fully remote, hourly contract role for security professionals curious about AI and tackling some of the most technically interesting problems in tech today. Flexible 10–40 hours/week with freelance autonomy and meaningful, high-impact work.

Qualifications

• Background in cybersecurity or application security.
• Familiar with threat modeling concepts applied to software systems, APIs, or emerging technologies.
• Analytically sharp — you think like an attacker and document like a defender.
• Naturally curious about edge cases, unintended behaviors, and the limits of complex systems.

Responsibilities

• Analyze AI and LLM security scenarios to understand model behavior under adversarial or edge-case conditions.
• Investigate prompt injection, data leakage risks, model abuse patterns, and system misuse cases.
• Classify security vulnerabilities and recommend mitigations based on real-world impact and likelihood.
• Evaluate AI system behavior and contribute structured findings to improve safety and reliability.
• Work with realistic, high-stakes scenarios drawn from cutting-edge AI deployment.

Skills

Cybersecurity

Threat modeling

Analytical thinking

Attention to detail

Independent working

Adversarial ML

Job description

Alignerr is seeking an AI Security Analyst to probe frontier AI models for vulnerabilities under adversarial conditions, helping ensure safety, reliability, and alignment with security standards.

This is a fully remote, hourly contract role for security professionals curious about AI and tackling some of the most technically interesting problems in tech today. Flexible 10–40 hours/week with freelance autonomy and meaningful, high-impact work.