Information Security Expert for AI Model Training

Design and execute adversarial red-team operations and hands-on security testing to help train next-generation AI systems for an enterprise SaaS customer. Your work will create realistic, high-quality inputs that shape how models learn, reason, and perform. No prior AI experience is required; deep real-world InfoSec expertise is the core requirement.

micro1 is an AI data lab that converts domain expertise into training data, evaluations, and feedback loops for frontier AI. Experts on this project contribute practical security knowledge to improve model safety and resilience.

• Design and define comprehensive red-teaming workflows and adversarial scenarios targeting SaaS and cloud environments.
• Conduct hands-on penetration testing and adversarial threat modeling across platforms such as Microsoft 365, Google Workspace, Slack, GitHub, and Snowflake.
• Act as a senior reviewer, evaluating the quality and depth of red-teaming exercises and deliverables.
• Identify and document potential vectors for misuse or manipulation of AI agents, including prompt injection, privilege escalation, data exfiltration, and destructive actions.
• Provide practical recommendations for security controls, policies, and detection strategies relevant to real-world SaaS deployments.
• Collaborate with other cybersecurity professionals, delivering detailed written and verbal feedback on findings and remediation options.
• Support benchmarking initiatives by creating adversarial scenarios that reflect contemporary threats and attack methodologies.

• Required skills: cybersecurity, penetration testing, red teaming.
• Extensive hands-on experience in red teaming, penetration testing, application or cloud security, or security engineering.
• Deep understanding of enterprise SaaS security concepts, including identity management, RBAC and permissions, and data governance.
• Direct familiarity with Microsoft 365, Google Workspace, Slack, GitHub, and Snowflake from a security evaluation perspective.
• Demonstrated ability to think adversarially about how AI and SaaS platforms could be exploited or compromised.
• Strong written and verbal communication skills for clear explanation of complex security issues and remediation guidance.
• Proven track record of practical, real-world impact on security projects beyond resume descriptions.
• Bonus: prior experience in AI or large language model security, or adversarial testing of agent-based systems.

• Engagement type: contractor role.
• Location: remote.
• Project focus: contribution to a high-impact initiative serving an enterprise SaaS customer.
• No prior AI experience required; subject matter expertise in InfoSec is the primary requirement.

• Pay rate: $60.00 to $100.00 per hour, paid on an hourly contractor basis.