What if your red team instincts and adversarial mindset could directly shape how AI understands and reasons about cybersecurity threats? We're looking for Offensive Security Analysts to analyze real-world attack paths, model adversary behavior, and help build the training data that powers next-generation AI systems.
This role is about structured adversarial reasoning — not exploit development. You'll work with realistic attack scenarios to map how threats propagate, where defenses break down, and how risk moves across modern environments. No zero-days required — just deep, practical knowledge of how real attacks actually unfold.
- Analyze attack paths, kill chains, and adversary strategies across realistic production environments
- Identify and classify weaknesses, misconfigurations, and defensive gaps
- Review red-team-style scenarios and intrusion narratives for accuracy and completeness
- Generate, label, and validate adversarial reasoning data used to train and evaluate frontier AI systems
- Clearly articulate attack chains, blast radius, and risk tradeoffs in structured written formats
- Work independently and asynchronously on task-based assignments — on your own schedule
Who You Are
- 2+ years in pentesting, red team operations, or a blue-team role with deep hands-on attack knowledge
- You understand how real attacks unfold — from initial access to lateral movement to impact
- Able to think like an attacker and communicate those thought processes clearly and precisely
- Comfortable analyzing complex threat scenarios and breaking them down into structured, reasoned outputs
- Detail-oriented and consistent — you don't cut corners when accuracy matters
Nice to Have
- Familiarity with frameworks like MITRE ATT&CK;, Cyber Kill Chain, or OWASP
- Experience writing threat models, attack narratives, or red team reports
- Background in cloud security, Active Directory environments, or enterprise network architecture
- Prior experience with AI tools or data annotation workflows
Why Join Us
- Work directly on frontier AI systems alongside leading research labs
- Fully remote and adaptable — work when and where it suits you
- Freelance autonomy with the structure of meaningful, high-impact work
- Contribute to AI that will shape how the industry understands and responds to cyber threats
- Potential for ongoing work and contract extension as new projects launch