Remote Offensive Security Analyst: AI Threat Modeling

Alignerr Corp.; Johannesburg; Remote; ZAR 907,000 - 2,042,000; Part time

Benefits offered by this job

Fully remote

Task-based work

Contract extension possible

Job summary

Alignerr is seeking Offensive Security Analysts to analyze attack paths, model adversary behavior, and help build training data for frontier AI systems. This role focuses on structured reasoning about how threats move across systems, not exploit development.

Fully remote with flexible hours and 10–40 hours per week. You’ll generate clear attack chains, assess impact, and contribute to ongoing AI-security projects with autonomy.

Qualifications

• 2+ years hands-on experience in pentesting, red teaming, or blue-team with offensive knowledge.
• Understand how real attacks unfold from initial access through lateral movement and impact.
• Able to explain complex attack chains clearly to technical audiences.
• Analytical and methodical thinker who spots gaps in systems.
• Strong written communicator documenting adversarial reasoning clearly.

Responsibilities

• Analyze attack paths, kill chains, and adversary strategies across production environments.
• Classify weaknesses, misconfigurations, and defensive gaps with structured explanations.
• Review red team-style scenarios and intrusion narratives for accuracy.
• Generate, label, and validate adversarial reasoning data to train AI systems.
• Articulate attack chains, potential impact, and security tradeoffs in writing.
• Work independently and asynchronously on task-based assignments.

Skills

Pentesting

Red teaming

Blue-team

Threat modeling

Adversary reasoning

Tools

MITRE ATT&CK

Cyber Kill Chain

OWASP

Job description

Alignerr is seeking Offensive Security Analysts to analyze attack paths, model adversary behavior, and help build training data for frontier AI systems. This role focuses on structured reasoning about how threats move across systems, not exploit development.

Fully remote with flexible hours and 10–40 hours per week. You’ll generate clear attack chains, assess impact, and contribute to ongoing AI-security projects with autonomy.