Member of Technical Staff (Senior Security Researcher)

Microsoft • ,

13d • $119,800 - $261,000

About The Position

Microsoft’s AI Red Team is seeking a Member of Technical Staff to test frontier and foundational AI models, products, and systems for security and safety failures. The role focuses on cyber and national security risks, including testing AI systems and agents, and contributes to techniques for evaluating high-risk models and applications before release. The team works with AI Safety, Security, and Product Development teams in sprint-based testing operations, helping inform internal business decisions and coaching developers on mitigating identified risks.

The role involves red teaming systems across Microsoft’s AI portfolio, including Bing Copilot, Security Copilot, GitHub Copilot, Office Copilot, and Windows Copilot. The interdisciplinary team includes red teamers, adversarial machine learning researchers, Responsible AI experts, and software developers. The position works with product groups and other security and development specialists to strengthen AI security defenses.

Requirements

• Bachelor’s degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or a related field and 4+ years of related experience; or a master’s degree in one of these fields and 3+ years of related experience; or a doctorate in one of these fields and 1+ year of related experience; or equivalent experience.
• Ability to meet Microsoft, customer, and/or government security screening requirements.
• Must pass the Microsoft background check and Microsoft Cloud background check upon hire or transfer and every two years thereafter.
• Must provide proof of country of citizenship, U.S. permanent residency, or other protected status to determine eligibility to access export-controlled information; citizenship will be verified with a valid passport, with other applicable documents accepted for lawful permanent residents, refugees, and asylees.

Nice To Haves

• Experience using common penetration testing tools such as Kali Linux, Burp Suite, Nmap, and Nessus.
• Familiarity with one or more programming languages, such as Python, C#, C/C++, or PowerShell.
• Background in development, red teaming, penetration testing, and national security.
• Experience testing agents; basic familiarity with AI or willingness to learn is desired. Prior knowledge of generative AI is not required.

Responsibilities

• Discover and exploit generative AI security vulnerabilities end-to-end, assessing AI systems for cyber and national security risks.
• Manage product group stakeholders as priority recipients and collaborators for operational sprints.
• Clarify communication and reporting for red teaming peers working with product groups.
• Develop methodologies and techniques to scale and accelerate cyber and national security AI red teaming in new and emerging threat areas, including open-source models.
• Work alongside traditional offensive security engineers, adversarial machine learning experts, and developers to deliver responsible AI operations.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior