AI Threat Architect — Offensive Security Analyst (Remote)

Alignerr Corp.; Cape Town; Remote; ZAR 344,000 - 620,000; Full time

Benefits offered by this job

Fully remote work

Flexible schedule

Contract autonomy

Meaningful, intellectually engaging工作

Job summary

Alignerr is seeking an Offensive Security Analyst (Structured / Non-Exploit) to inform how AI understands and reasons about real-world threats. This remote, hourly contract role involves analyzing adversarial attack paths, modeling threat behavior, and contributing to safe AI training data.

Commitment ranges from 10–40 hours per week. You will work independently on task-based assignments, mapping attack chains, and identifying where defenses fail across diverse environments to produce precise,

Qualifications

• 2+ years of hands-on pentesting, red teaming, or blue-team experience.
• Ability to clearly explain attack chains, attacker objectives, and defensive implications.
• Systematic, detail-oriented approach with adversary mindset and end-to-end threat mapping.
• Strong written communication translating complex concepts into structured analyses.

Responsibilities

• Analyze real-world attack paths, kill chains, and adversary strategies across modern environments.
• Classify weaknesses, misconfigurations, and defensive gaps in realistic system scenarios.
• Review and evaluate red team-style scenarios and intrusion narratives for technical accuracy and depth.
• Generate, label, and validate adversarial reasoning data used to train and evaluate frontier AI systems.
• Articulate how attacks unfold, their impacts, and the defender tradeoffs in clear, structured language.
• Work independently and asynchronously on task-based assignments at your own pace.

Skills

Pentesting

Red teaming

Blue-team

Threat modeling

Adversary mindset

Tools

MITRE ATT&CK

Active Directory

Job description

Alignerr is seeking an Offensive Security Analyst (Structured / Non-Exploit) to inform how AI understands and reasons about real-world threats. This remote, hourly contract role involves analyzing adversarial attack paths, modeling threat behavior, and contributing to safe AI training data.

Commitment ranges from 10–40 hours per week. You will work independently on task-based assignments, mapping attack chains, and identifying where defenses fail across diverse environments to produce precise,