About this role · Stem
About the Role What if your ability to think like an adversary could directly shape how AI understands cybersecurity threats? We're looking for offensive security professionals to analyze real-world attack paths, adversary behavior, and defensive gaps — and use that expertise to help train and evaluate cutting-edge AI systems. This is not an exploit development role. It's about structured adversarial reasoning: modeling how threats move through systems, where defenses fail, and how risk propagates across modern environments. Your insights go directly into frontier AI research. - 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 in system architectures - Review red-team-style scenarios and intrusion narratives for accuracy, completeness, and realism - Generate, label, and validate adversarial reasoning data used to train and evaluate AI models - Clearly articulate attack chains, potential impact, and security tradeoffs in structured formats - Work independently and asynchronously — fully on your own schedule Who You Are - 2+ years of hands-on experience in penetration testing, red teaming, or an offensive-minded blue team role - Deep understanding of how real attacks unfold in production environments — not just theory - Able to break down complex attack chains and communicate them clearly in writing - Comfortable working with realistic threat scenarios without needing to develop or deploy actual exploits - Detail-oriented, self-motivated, and reliable when working independently Nice to Have - Familiarity with frameworks like MITRE ATT&CK, kill chain modeling, or threat intelligence - Experience in threat modeling, purple team exercises, or security architecture review - Background in cloud security, Active Directory environments, or enterprise network defense - Certifications such as OSCP, CEH, GPEN, or equivalent practical experience - Prior involvement in AI, data labeling, or structured annotation workflows Why Join Us - Work directly on frontier AI systems alongside leading 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 a genuinely new and impactful domain - Potential for ongoing work and contract extension as new projects launch