About OpenTrain
OpenTrain is the centralized, open platform where AI training and data-labeling freelancers find work, consolidate opportunities across platforms, and build a unified AI training portfolio they control. We make specialized AI training work easier to track, apply for, and grow into a durable freelance career.
About this role
OpenTrain is recruiting for a Government Security AI Red Teaming Expert to evaluate how malicious actors might use large language models to plan or enhance violence, terrorism, targeted assassinations, special operations, and tactical attacks. You will interpret model outputs from jailbreaking attempts, assess highly actionable guidance and executable tactics, and determine whether generated content presents a credible material threat in a real-world scenario. This work supports AI safety research and threat detection frameworks with direct government security implications.
What you will do
- Simulate malicious use cases involving large language models and government security threats
- Red team model behavior and review outputs generated through jailbreaking attempts
- Assess procedural instructions, executable tactics, and domain-specific knowledge for security relevance
- Decide whether model-generated content constitutes a credible, material real-world threat
- Apply operational, analytic, or planning judgment to ambiguous and sensitive scenarios
- Review content that may be sensitive or graphic and identify implications for threat detection and response
Required skills
- Seasoned firsthand experience in intelligence, defense, federal law enforcement, special operations, counterterrorism, cyber operations, or related government security work
- Background as an analyst, operator, or planner, including experience with counterterrorism, counterintelligence, asymmetric warfare, unconventional operations, threat finance, targeting, wargaming, or red teaming
- Strong judgment when interpreting ambiguous threat scenarios and highly actionable guidance
- Ability to review sensitive or graphic material for security relevance
Helpful background
Advanced study from military graduate programs such as SAMS, JAWS, or NDU, or from security-focused civilian programs such as an MPP, MPA, or MA in Security Studies, is welcome. Undergraduate education from a service academy paired with real-world operational assignments is also relevant.
Work arrangement
This is remote, asynchronous work with flexible scheduling and an expected commitment of approximately 10 to 20 hours per week. Compensation is advertised at up to $200 per hour. OpenTrain helps specialized freelancers consolidate AI training opportunities across platforms and build a durable AI training portfolio.