Apply adversarial thinking to frontier AI systems as a remote Offensive Security Analyst using attack-path analysis and cybersecurity expertise.

Alignerr seeks Offensive Security Analysts for hourly contract work supporting AI development. You will analyze how real attacks unfold, then help train and evaluate models reasoning about cybersecurity. The work emphasizes attack chains, adversary objectives, and clear written assessments rather than exploitation.

Key Responsibilities:

- Analyze realistic attack paths, kill chains, and adversary strategies
- Classify weaknesses, misconfigurations, and defensive gaps
- Review intrusion scenarios for accuracy and completeness
- Generate and validate adversarial reasoning data
- Explain attack chains, impact, and security tradeoffs

Requirements:

- Two or more years in pentesting, red teaming, or blue teaming
- Understanding of real production attacks beyond theory
- Ability to explain complex attack chains clearly
- Structured, detail-oriented analytical approach
- Comfort producing written assessments and structured data

Bring offensive security judgment, attack-chain analysis, and transparent writing to Alignerr’s remote AI evaluation work.

📌 Offensive Security AI Analyst (Toronto)
🏢 Alignerr
📍 Toronto