Offensive Security Analyst (Structured / Non-Exploit)
About this role
About the Role What if your offensive security knowledge could directly shape how AI understands cyber threats, attack paths, and adversary behavior — at a frontier level? We're looking for experienced security professionals to work on structured adversarial reasoning projects for cutting-edge AI systems. This role is built for practitioners who think like attackers: people who can dissect a kill chain, identify where defenses break down, and articulate how risk propagates across complex environments. No exploit development required. Just sharp, structured thinking about how real attacks unfold — and the ability to communicate that clearly. - Organization: Alignerr - Type: Hourly Contract - Location: Remote - Commitment: 10–40 hours/week What You'll Do - Analyze attack paths, kill chains, and adversary strategies across realistic production environments - Identify and classify weaknesses, misconfigurations, and defensive gaps with precision - Review red team-style scenarios and intrusion narratives for accuracy, depth, and strategic logic - Generate, label, and validate adversarial reasoning data used to train and evaluate AI security models - Clearly explain attack chains, impact assessments, and risk tradeoffs in structured formats - Work independently and asynchronously on task-based assignments — fully on your own schedule Who You Are - 2+ years of hands-on experience in pentesting, red teaming, or a blue-team role with deep offensive knowledge - You understand how real attacks unfold in production environments — not just in theory - You can walk through a full attack narrative: initial access, lateral movement, persistence, and impact - You think in systems — you see how weaknesses chain together and where defenses actually fail - You communicate complex security concepts clearly and precisely in writing - No AI background required — your security expertise is what matters Nice to Have - Familiarity with threat intelligence frameworks such as MITRE ATT&CK - Experience with cloud, Active Directory, or enterprise network attack paths - Background in red team operations, adversary simulation, or threat hunting - Exposure to security architecture review or risk modeling - Prior experience contributing to security training, documentation, or research Why Join Us - Work directly on frontier AI systems alongside leading AI research labs - Fully remote and flexible — work when and where it suits you - Freelance autonomy with the structure of meaningful, task-based work - Apply your offensive security expertise to one of the most consequential technology challenges of our time - Potential for ongoing work and contract extension as new projects launch
Application listings
Choose a source listing and check its country requirements.