Microsoft
Member of Technical Staff (Senior Security Researcher)
$120K–$261K
United States · On-site · Staff · Full-time · Posted Oct 28, 2026
- Experience
- 4+ years with a bachelor’s degree, 3+ years with a master’s degree, or 1+ year with a doctorate; equivalent experience is accepted.
- Education
- Bachelor’s, master’s, or doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or a related field; or equivalent experience.
About the job
Red-team Microsoft AI models and applications to uncover cyber and national security risks, develop testing methods, and help product teams strengthen defenses before launch.
What you'll do
- Discover and exploit GenAI security vulnerabilities in AI systems, with a focus on cyber and national security.
- Coordinate operational testing sprints with product stakeholders and communicate findings to red-team peers and product groups.
- Develop scalable AI red-teaming methods and work with security engineers, adversarial ML experts, and developers.
What they ask for
- Bachelor’s degree in a listed or related field and 4+ years of related experience; or master’s degree and 3+ years; or doctorate and 1+ year; or equivalent experience.
- Ability to meet required Microsoft, customer, and/or government security screening requirements.
- Pass the Microsoft background and Microsoft Cloud background check upon hire or transfer and every two years thereafter.
- Provide citizenship or qualifying status documentation and citizenship verification for export-control access eligibility.
Nice to have
- Experience with common penetration-testing tools, such as Kali Linux, Burpsuite, Nmap, or Nessus.
- Programming-language familiarity, experience testing agents, or a background in development, red teaming, pentesting, and national security.
Pay
USD $119,800 - $234,700 per year (base pay); USD $160,200 - $261,000 per year (base pay)
Tools
Kali Linux, Burpsuite, Nmap, Nessus, Python, C#, C/C++, PowerShell
AI focus
Red-team frontier and foundational AI models, agents, and applications for cyber and national security vulnerabilities; develop testing methods and support safer AI deployment.
Model-written summary · the original posting is authoritative