AI Adversarial Security Analyst — Remote Contract

Alignerr Corp.; Montreal; Remote; CAD 83,000 - 138,000; Full time

Benefits offered by this job

Fully remote

Flexible schedule

Contractual freelance work

Job summary

Alignerr is seeking an Offensive Security Analyst to apply adversarial reasoning to AI training and evaluation. This fully remote, hourly contract role focuses on structured thinking about attacks rather than exploit development.

You will analyze attack paths, identify gaps in complex architectures, and translate insights into concrete narratives for AI systems, with 10–40 hours per week on your own schedule.

Qualifications

• 2+ years of hands-on pentesting, red/blue team security with deep attack knowledge.
• Understand how real attacks unfold in live production environments.
• Break down complex attack chains and communicate clearly.
• Comfortable with ambiguity and applying structured thinking to security scenarios.
• Detail-oriented with rigorous analysis.

Responsibilities

• Analyze attack paths, kill chains, and adversary strategies across production-style environments.
• Identify weaknesses, misconfigurations, and defensive gaps in complex architectures.
• Review red-team narratives and threat modeling exercises.
• Generate, label, and validate adversarial reasoning data for AI training and benchmarking.
• Articulate attack chains and business impact in structured formats.
• Work independently and asynchronously on your own schedule.

Skills

Threat modeling

Adversary simulation

Pentesting

Red team

Blue team security

Tools

MITRE ATT&CK

STRIDE

PASTA

Job description

Alignerr is seeking an Offensive Security Analyst to apply adversarial reasoning to AI training and evaluation. This fully remote, hourly contract role focuses on structured thinking about attacks rather than exploit development.

You will analyze attack paths, identify gaps in complex architectures, and translate insights into concrete narratives for AI systems, with 10–40 hours per week on your own schedule.