InfoSec Red Teaming Expert

About OpenTrain

OpenTrain is the #1 platform for finding and building careers in AI training and data labeling. We connect skilled contractors with specialized projects that help teach and evaluate AI systems while allowing contributors to build a durable, centralized portfolio of their AI training work.

We hire practitioners directly as contractors for focused, real-world tasks — from security testing and red teaming to annotation, evaluation, and benchmarking. This role is part-time, remote, and tailored for experienced security professionals who want flexible freelance work that directly shapes next-generation AI systems.

Why AI training and red teaming matters

AI systems learn from human-crafted examples, judgments, and adversarial tests. Security-focused contributions — designing adversarial scenarios, documenting abuse paths, and evaluating mitigations — are critical to making AI safe and reliable in enterprise settings.

This work is accessible, flexible, and impactful: you can contribute remotely, choose hours that fit your schedule, and apply practical cybersecurity expertise to influence how models and agents behave in real-world SaaS environments.

The role — InfoSec Red Teaming Expert

You will design and evaluate adversarial workflows that expose realistic abuse vectors in SaaS and cloud-based environments, review red-teaming deliverables, and document attack paths relevant to enterprise tools and AI agents.

This is a contract, part-time engagement requiring 20+ hours per week. Pay is hourly, with a range of $60–$100 USD per hour depending on experience and the task.

• Design red-teaming workflows and adversarial scenarios for SaaS and cloud environments.
• Perform hands-on penetration testing and adversarial threat modeling across enterprise platforms.
• Review and evaluate the quality and depth of red-teaming exercises and deliverables.
• Document misuse vectors such as prompt injection, privilege escalation, data exfiltration, and destructive actions.
• Contribute security insights for controls, policies, and detection strategies.
• Build benchmarking scenarios that reflect contemporary threats and attack methods.
• Collaborate with cybersecurity professionals through detailed written and verbal feedback.

Requirements

We are looking for contractors with practical, hands-on security experience and strong adversarial judgment. The role emphasizes real-world impact: demonstrable testing, clear technical communication, and the ability to translate findings into usable mitigation guidance.

• Extensive hands-on experience in red teaming, penetration testing, application security, cloud security, or security engineering.
• Deep understanding of enterprise SaaS security, including identity, RBAC/permissions, and data governance.
• Direct familiarity with Microsoft 365, Google Workspace, Slack, GitHub, or Snowflake from a security evaluation perspective.
• Ability to identify prompt injection, privilege escalation, data exfiltration, and destructive actions.
• Strong written and verbal communication skills for explaining findings and remediations.
• Practical security experience with observable, real-world impact (beyond resume-only exposure).

Helpful background (not required)

The following experience is a plus and will help you onboard faster, but candidates without it may still be considered if core requirements are met.

• Prior experience in AI or LLM security.
• Experience testing agent-based systems and emergent behavior exploitation.

Who should apply and how it works

This opportunity is ideal for cybersecurity contractors who want to apply specialized red-teaming and cloud/SaaS security expertise in a flexible, remote setting while building an AI training portfolio on OpenTrain.

You will be hired as a contractor and paid hourly. Work is worldwide (English required), part-time with a 20+ hrs/week expectation. Tasks include designing adversarial tests, hands-on evaluations, reviewing deliverables, and documenting misuse vectors that inform AI training and security benchmarks.

• Employment type: Contractor, Part-time. Time requirement: 20+ hours/week. Language: English. Worldwide applicants accepted.
• Pay: Hourly, USD $60–$100/hr.
• Labeling/task types: Red teaming, evaluation/rating, and data collection for security benchmarking.