below marketmost similar roles pay hereabove market
This role pays less than
52%
of similar roles. Most pay
$159,000–$216,250
— the blue band above.
At the midpoint, this role pays about
$177k
versus about
$188k
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
676 open roles
on FindRole.
Listed pay typically runs
$119,800–$234,700
across 630 roles with salary data.
The Senior Security Researcher - Red Team joins a new team focused on agent security, offensive security, cloud identity, attack automation, and adversarial AI. In this role, you will conduct hands-on red teaming of agentic systems and AI-enabled security products. You will design realistic attack chains across models, tools, identities, permissions, and isolation boundaries while investigating issues like indirect prompt injection, privilege escalation, and sandbox escapes. You will build automated attack suites, high-fidelity test environments, and rigorous threat models to produce reproducible evidence for engineering and product teams. Required skills include expertise in offensive security, cloud identity, or application security, along with programming ability to build exploit prototypes. You will solve technical problems regarding secure agent architecture, least-privilege design, and human-in-the-loop controls.
Design and execute end-to-end attacks against agentic systems, AI-enabled security products, and orchestration frameworks.
Investigate vulnerabilities including indirect prompt injection, privilege escalation, sandbox escapes, and cross-agent manipulation.
Build realistic attack chains using attacker-controlled telemetry, code, and web content encountered in production workflows.
Develop automated attack suites and high-fidelity test environments to continuously exercise model behavior and logic.
Create rigorous threat models and reproducible evidence to assess exploitability and customer impact.
Convert confirmed weaknesses into regression evaluations, automated tests, and stronger authorization boundaries.
Track emerging agent attack techniques and real-world adversary behavior to evolve internal methods and tooling.
What we're looking for
Must have a Doctorate in a relevant field, or a Master's degree with 3+ years of research experience, or a Bachelor's degree with 4+ years of research experience.
Equivalent experience to the listed educational and research requirements is accepted.
Must be able to pass the Microsoft Cloud background check upon hire and every two years thereafter.
Hands-on expertise in offensive security, agent security, cloud or identity security, application security, exploitation, or a closely related discipline (preferred).
Experience designing security investigations that produce reproducible technical evidence and actionable remediation (preferred).
Programming and engineering ability sufficient to build attack tooling, test harnesses, exploit prototypes, and automated security tests (preferred).
Experience testing large language models, agentic systems, tool use, plugins, connectors, multi-agent orchestration, or AI-enabled security products (preferred).
Experience with indirect prompt injection, cloud identity, authorization, sandboxing, container security, web or application exploitation, or offensive-security operations (preferred).
Adversarial Machine Learning
Offensive Security
Red Teaming
Large Language Models
Agentic Systems
Attack Automation
Privacy
Predictive Analytics
Statistics
Prompt Injection
Security Research
Regression Evaluation
Vulnerability Research
Offensive Security
Exploit Development
Reverse Engineering
AI
Threat Analysis
Anomaly Detection
Software Development Lifecycle
Cybersecurity
Capture The Flag (CTF)
Vulnerability Research
C
C++
Windows
Linux
Exploit Development
AI
Software Development Lifecycle
Threat Analysis
Anomaly Detection
Virtualization Security
Security Mitigations
Automation
Linux
C
C++
Python
PowerShell
Reverse Engineering
Malware Analysis
Vulnerability Research
Anomaly Detection
Network Protocols
Debuggers
Disassemblers
Sandboxes
MacOS
Mobile Platforms
Software Development Lifecycle
Azure
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