Remote Offensive Security Analyst for AI Threat Modeling

Alignerr Corp.; Boston (MA); Remote; USD 83,000 - 124,000; Part time

Job summary

Alignerr is seeking an Offensive Security Analyst to study attack paths and model adversary behavior for training frontier AI systems. The role emphasizes adversarial reasoning and producing high-quality structured data from real-world scenarios.

You will work remotely as an hourly contractor, with a commitment of 10–40 hours per week, and contribute to AI safety and cyber threat understanding in production environments.

Qualifications

• 2+ years hands-on experience in penetration testing, red team operations, or a blue team role with offensive knowledge.
• Ability to analyze real-world attack paths and translate into structured data for AI training.
• Strong written communication to clearly convey adversary thinking and tradeoffs.

Responsibilities

• Analyze attack paths, kill chains, and adversary strategies across realistic, real-world system scenarios.
• Identify weaknesses, misconfigurations, and defensive gaps and explain risk implications.
• Review and evaluate red team scenarios and intrusion narratives for accuracy and depth.
• Generate, label, and validate adversarial reasoning data used to train AI systems.
• Clearly articulate attack chains, business impact, and security tradeoffs in structured formats.
• Work independently and asynchronously on task-based assignments.

Skills

Penetration testing

Red team operations

Blue team defense

Job description

Alignerr is seeking an Offensive Security Analyst to study attack paths and model adversary behavior for training frontier AI systems. The role emphasizes adversarial reasoning and producing high-quality structured data from real-world scenarios.

You will work remotely as an hourly contractor, with a commitment of 10–40 hours per week, and contribute to AI safety and cyber threat understanding in production environments.