Drimva

Microsoft

Member of Technical Staff (Senior AI Security Researcher)

$120K–$261K

United States · On-site · Staff · Full-time · Posted Oct 29, 2026

Experience
4+ years with a bachelor’s degree, 3+ years with a master’s degree, or 1+ year with a doctorate; or equivalent experience.
Education
Bachelor's, Master's, or Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field, or equivalent experience.

About the job

Conduct applied AI security research on coordinated adversarial agents, developing ways to observe, detect, attribute, interrupt, and contain agent swarms.

What you'll do

  • Lead research into adversarial AI agents and coordinated multi-agent behavior; characterize coordination, behavioral signatures, provenance, and adaptation.
  • Build instrumented environments and evaluate detection and containment methods across changing models, tools, topologies, and conditions.
  • Produce reproducible evaluation assets and security guidance for red-team and defense partners.

What they ask for

  • Bachelor’s degree in a listed or related field and 4+ years of related experience, or a master’s degree and 3+ years, or a doctorate and 1+ year, or equivalent experience.
  • Ability to meet Microsoft, customer and/or government security screening requirements, including the Microsoft Cloud Background Check.

Nice to have

  • Experience in agentic AI security, adversarial machine learning, cybersecurity, or coordinated-agent research and experimentation.
  • Demonstrated research leadership or outputs such as peer-reviewed publications, patents, or released research software; hands-on Python and machine-learning-framework proficiency.

Pay

USD $119,800 - $234,700 per year (base salary); USD $160,200 - $261,000 per year (base salary)

Tools

Python

AI focus

Research adversarial AI-agent systems, especially coordinated and swarm-like behavior, and develop and evaluate methods to detect, attribute, interrupt, and contain offensive agent swarms.

Model-written summary · the original posting is authoritative

First seen Oct 30, 2026 · Last verified Nov 6, 2026 (UTC)