Provide technical leadership on cross-functional teams performing AI adversarial threat analysis to identify and characterize vulnerabilities in real-world national security systems
Work across military and intelligence community sponsors to understand shared needs and technologies
Utilize and enhance MITRE ATLAS framework for assessing threats to AI-enabled systems
Assess and design AI systems for threat detection, monitoring, and reporting
Provide thought leadership supporting the innovation of new AI capabilities applied to cyber operational challenges
Lead research, development, engineering, evaluation, and integration of secure AI systems to protect national security systems.
Compensation
$143,600 - $179,500 - $215,400 Annual
Responsibilities
Perform AI adversarial threat analysis to identify and characterize vulnerabilities in real-world national security systems
Work across military and intelligence community sponsors to understand shared needs and technologies
Utilize and enhance MITRE ATLAS framework for assessing threats to AI-enabled systems
Contribute to the innovation of new AI capabilities applied to cyber operational challenges
Convey complex ideas to non-technical audiences through briefings and/or white papers
Requirements
Bachelor’s degree in a relevant field
Master’s degree
PhD
Nice to have: Advanced degree in computer science, engineering, or related disciplines
Nice to have: Track record of successful deployment of AI/ML systems or components used by customers or stakeholders outside of a lab/experimental setting
Lead technical and research engineer focused on adversarial AI threat analysis, defense development, and integration into national security systems.
Locations (2)
Fort Meade, Maryland, United States
Annapolis Junction, Maryland, United States
Compensation
$174,000 - $217,500 - $261,000 Annual
Responsibilities
Provide technical leadership on cross-functional teams performing AI adversarial threat analysis to identify and characterize vulnerabilities in real-world national security systems
Work across military and intelligence community sponsors to understand shared needs and technologies
Provide thought leadership supporting the innovation of new AI capabilities applied to cyber operational challenges
Convey complex ideas to non-technical audiences through briefings and/or white papers
Lead, mentor, and collaborate with technical staff
Seeking agent and systems red teamers to join a red team spanning agent security, offensive security, cloud identity, attack automation and adversarial AI.
Compensation
typical base pay range for this role across the U.S. is $119,800 - $234,700 per year. There is a different range applicable to specific locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is $160,200 - $261,000 per year.
Responsibilities
Conduct hands-on red teaming of agentic systems and AI-enabled security products
Design realistic attack chains across models, tools, identities, permissions and isolation boundaries
Design and execute attack-based security tests
Investigate indirect prompt injection and security vulnerabilities
Convert security findings into production mitigations, automated tests, and architectural changes
Lead AI Security EngineerThe Mitre Corporation · McLean, US