Senior Adversarial AI Engineer

• Typically requires a minimum of 5 years of experience in artificial intelligence with a Bachelor’s degree in a relevant field; or 3 years and a Master’s degree; or a PhD with relevant experience who can immediately contribute at this job step; or equivalent combination of AI-related education and work experience
• Hands-on experience in one or more of the following technical areas: Generative AI, AI Security, Agentic AI, AI Testing & Evaluation, or Applied AI
• Demonstrated skills with Python and the standard AI technical stack
• Ability to work independently to learn new technologies, methods, processes, frameworks/platforms, and systems
• Excellent written and verbal communication skills to articulate challenging technical concepts to both lay and expert audiences
• Active IC or DOD TS/SCI security clearance with CI Poly
• Per the U.S. Government’s eligibility requirements, you must be a U.S Citizen to be considered for a security clearance.
• This position requires a minimum of 3 days a week on-site, * Advanced degree in computer science, engineering, or related disciplines
• Hands-on experience in one or more of the following technical areas: AI red teaming, AI threat analysis, AI-enhanced cybersecurity, or AI-accelerated cyber operations
• Experience generating or analyzing intelligence reporting data
• Familiarity with MITRE ATLAS threat matrix
• Experience leading small to medium sized teams to solve practical technical challenges

This requisition requires the candidate to have a minimum of the following clearance(s)

At MITRE, your passion fuels work that impacts our nation and improves lives. This is where your skills strengthen national security, cybersecurity, health, transportation, and citizen services. We’re a nonprofit engineering, applied research, and advanced technology organization working in the public interest. With objectivity and integrity at our core, we lead federally funded research and development centers for U.S. government agencies - collaborating with industry and academia to deliver integrated, high-impact solutions that advance our nation’s health, security, and prosperity. Our people tackle the toughest technical challenges, supported by competitive benefits, meaningful career development, and a culture of innovation, collaboration, and technical excellence. Choose MITRE for a career with purpose - and help shape the future.

MITRE’s Trustworthy & Secure AI (TSAI) Department consists of a diverse team united by a passion and a sense of urgency to harness trustworthy and assured artificial intelligence (AI) to help solve problems in the public interest. The TSAI Department supports our sponsors’ missions by delivering capabilities for securing and increasing trust in AI-enabled systems, including data driven AI risk awareness and mitigation, AI red teaming, and trusted tools and techniques for applying AI in high consequence environments. The TSAI Department works across government, industry, and academia to provide, assess, and shape trustworthy and secure AI systems to address complex mission needs for our sponsors. Our work provides opportunities to address real-world challenges in the rapidly developing field of AI assurance, and to research and prototype new methods to address mission needs. We are looking for highly motivated, adaptive, and self-directed candidates to perform research, development, engineering, evaluation, and integration of secure AI systems.

Roles & Responsibilities:

The position involves assessing threats to AI systems, research and development of defenses and mitigations against adversarial AI tactics and techniques. Specific responsibilities will include:

• Perform AI adversarial threat analysis to identify and characterize vulnerabilities in real-world national security systems
• Work as a technical subject matter expert within a team of intelligence analysts to research, analyze and produce intelligence reports
• Assessing threats to AI-enabled systems and use of AI by adversaries
• Convey complex ideas to non-technical audiences through intelligence production, briefings and/or white papers