Red Team Lead (Offensive Cybersecurity)

micro1 is seeking an experienced Red Team Lead to contribute specialized offensive cybersecurity expertise to a critical project focused on training next-generation AI systems. In this role, you will leverage your deep domain knowledge to shape how models learn and reason by providing high-quality, real-world input, ensuring that AI development is informed by advanced security perspectives.

Key responsibilities

• Develop comprehensive taxonomies for cyber-capability tasks and attack stages relevant to modern threat landscapes.
• Design and validate evaluation frameworks for offensive security, focusing on real-world scenarios involving exploit chains, malware, cloud/appsec, and social engineering.
• Create safe and effective proxy tasks to simulate advanced attack vectors while maintaining strict boundaries and ethical controls.
• Formulate robust scoring rubrics to assess attack sophistication, coverage, and impact across diverse domains.
• Review, critique, and enhance benchmarks for red team operations to ensure alignment with evolving security risks and best practices.

Requirements

• 5+ years of hands-on experience in offensive cybersecurity, red teaming, exploit development, or vulnerability research.
• Proven track record as a principal security engineer, exploit developer, cloud red-team lead, or malware reverse-engineer.
• Deep expertise in cyber attack methodologies, exploit chains, and cloud/application security assessments.
• Strong background in malware analysis, reverse engineering, and social engineering tactics.
• Demonstrated ability to produce clear, actionable written and verbal communication for diverse audiences.

What we offer

• Opportunity to influence the development of cutting-edge AI systems through expert security insights.
• Fully remote work environment allowing for asynchronous collaboration with global stakeholders.
• Engagement in high-impact, complex cybersecurity projects that challenge your technical expertise.