below marketmost similar roles pay hereabove market
This role pays less than
62%
of similar roles. Most pay
$162,000–$235,025
— the blue band above.
At the midpoint, this role pays about
$177k
versus about
$199k
for comparable roles.
Based on 240 similar postings.
Employer
About Microsoft
Microsoft Corporation is a global technology leader producing software, hardware, and cloud services including Windows, Office 365, Azure cloud platform, Xbox gaming, and Surface devices. Industry: Software & Cloud Computing
Microsoft currently has
636 open roles
on FindRole.
Listed pay typically runs
$119,800–$234,700
across 591 roles with salary data.
Member of Technical Staff (Senior AI Security Researcher) joins the Microsoft Red Team to conduct forward-looking AI security research. This role focuses on researching adversarial AI-agent systems, specifically emphasizing coordinated and swarm-like behaviors. You will build instrumented environments to characterize campaigns, identify behavioral signatures, trace provenance, and evaluate methods for interrupting and containing coordinated offensive agent swarms. Key responsibilities include stress-testing methods across changing models, tools, and topologies to identify evasion paths and failure modes while producing reproducible evaluation assets and security guidance. The role requires expertise in statistics, computer science, or related fields, with a focus on adversarial machine learning and threat detection. Candidates should demonstrate hands-on proficiency with Python and machine learning frameworks to prototype and experiment with agentic AI security and behavioral analysis.
Lead applied research on adversarial AI agents and coordinated multi-agent or swarm-like behavior.
Characterize coordination patterns, behavioral signatures, provenance, and adaptation across agent populations.
Build instrumented environments to observe and measure agent coordination under controlled security scenarios.
Develop and evaluate methods to detect, attribute, interrupt, and contain coordinated offensive agent swarms.
Stress-test security methods across changing models, tools, topologies, and operating conditions to identify evasion paths.
Produce reproducible evaluation assets and security guidance for red-team and defense partners.
What we're looking for
Bachelor's degree in a related field and 4+ years of experience, Master's and 3+ years, or Doctorate and 1+ year of experience.
Equivalent experience to the degree and years of experience requirements.
Ability to pass the Microsoft Cloud Background Check.
Ability to meet Microsoft, customer, and/or government security screening requirements.
Prior research or engineering experience in agentic AI security, including coordinated, multi-agent, or swarm-like behavior (preferred).
Demonstrated record of independently leading complex research projects from problem formulation through reproducible results and partner adoption (preferred).
Peer-reviewed publications, patents, or released research software in agentic AI security, adversarial machine learning, or threat detection (preferred).
Hands-on proficiency with Python and machine learning frameworks for research prototyping and experimentation (preferred).
Generative AI
Adversarial Machine Learning
Red Teaming
Penetration Testing
Python
C#
C/C++
PowerShell
Kali Linux
Burpsuite
Nmap
Nessus
Cybersecurity
National Security
Predictive Analytics
Statistics
Open Source Models
AI Security
LLM
RAG
Python
Red Teaming
Prompt Injection
MITRE ATLAS
OWASP Top 10 for LLM Applications
Vulnerability Research
Penetration Testing
Agentic AI
Fine-tuning
Data Exfiltration
Anomaly Detection
Software Development Lifecycle
Large-scale Computing
Responsible AI
Vulnerability Research
Offensive Security
Exploit Development
Reverse Engineering
AI
Threat Analysis
Anomaly Detection
Software Development Lifecycle
Cybersecurity
Capture The Flag (CTF)
Machine Learning
AI Security
Generative AI
Large Language Models
Adversarial Machine Learning
Data Analytics
Natural Language Processing
Computer Vision
Containerization
Microservices
Data Visualization
NetFlow
Cybersecurity
Statistical Modeling
System Design