AI Security Adversary Analyst - Remote Contract

Alignerr Corp.; Chicago (IL); Remote; USD 55,000 - 103,000; Full time

Job summary

Alignerr is seeking an Offensive Security Analyst to bring real-world attack knowledge to frontier AI training. This role emphasizes structured adversarial reasoning over exploit development, using realistic threat scenarios to show how attacks unfold and where defenses fail.

You will work asynchronously on task-based assignments, analyze kill chains, identify weaknesses, and help label data used to train AI security models. Remote, hourly contract with flexible hours, 10–40 hours per week.

Qualifications

• 2+ years hands-on experience in pen testing, red teaming, or blue-team with deep attack knowledge.
• Understanding how real attacks unfold in production environments.
• Ability to break down complex attack chains and write clearly.

Responsibilities

• Analyze attack paths, kill chains, and adversary strategies across realistic environments.
• Identify and classify weaknesses, misconfigurations, and defensive gaps.
• Review red-team scenarios for accuracy and adversarial realism.
• Generate, label, and validate adversarial reasoning data to train AI systems.
• Clearly articulate attack chains, impact, and risk in structured formats.
• Work independently and asynchronously on task-based assignments.

Skills

Penetration testing

Red team knowledge

Blue team experience

Job description

Alignerr is seeking an Offensive Security Analyst to bring real-world attack knowledge to frontier AI training. This role emphasizes structured adversarial reasoning over exploit development, using realistic threat scenarios to show how attacks unfold and where defenses fail.

You will work asynchronously on task-based assignments, analyze kill chains, identify weaknesses, and help label data used to train AI security models. Remote, hourly contract with flexible hours, 10–40 hours per week.