Overview In this role you will advance secure AI by researching vulnerabilities in AI/ML systems and developing defenses. You'll join the Secure AI Lab, collaborating with cross-discipline teams to translate research into prototype solutions for government sponsors. You will drive original work, publish findings, and guide others while shaping a national agenda for AI security. This position blends hands-on research with strategy, mentorship, and stakeholder engagement to elevate trustworthy AI for mission-critical use.
Responsibilities- Conduct and lead novel research in applied ML and AI security, with a focus on vulnerabilities and defenses.
- Develop prototypes and operational capabilities for government customers through interdisciplinary collaboration.
- Plan and influence overall research strategy and contribute to national AI security agenda.
- Collaborate with researchers, developers, designers, and technical leads; build relationships with sponsors.
- Mentor junior team members and contribute to knowledge sharing across the division.
- Publish research artifacts and prepare proposals or pitches for new projects.
- Transition research findings into actionable guidance for government sponsors.
Key requirements- Bachelor's degree in computer science, statistics, machine learning, electrical engineering, or related discipline with 10 years of experience OR MS with 8 years OR PhD with 5 years
- Willingness to work onsite at an SEI facility 5 days per week
- Ability to obtain and maintain an active Department of War security clearance
- Willingness to travel up to 25% of the time to sponsor sites and conferences
- Strong written and verbal communication skills; ability to explain complex ideas to non-experts
- Experience leading research projects in novel areas with limited prior work to build upon
- Experience publishing technical artifacts and presenting research findings
- Ability to plan, develop, and deliver an overall research strategy with leadership
- collaboration
- strong communication
- mentoring and teaching
- machine learning
- adversarial machine learning (preferred)
- research methods
