Senior AI Security Researcher

Share job

Security represents the most critical priorities for our customers in a world awash in digital threats, regulatory scrutiny, and estate complexity. Microsoft Security aspires to make the world a safer place for all. We want to reshape security and empower every user, customer, and developer with a security cloud that protects them with end to end, simplified solutions. The Microsoft Security organization accelerates Microsoft’s mission and bold ambitions to ensure that our company and industry is securing digital technology platforms, devices, and clouds in our customers’ heterogeneous environments, as well as ensuring the security of our own internal estate.

The Microsoft Security Response Center (MSRC) is looking for researchers to join us in protecting AI systems, and the users of these systems, from threats to security and privacy. This role offers a unique opportunity to solve real-world security and privacy challenges, through cutting-edge scientific research, informed by vulnerability data from production AI systems, leading to mitigations or new techniques that can be deployed at Microsoft and beyond. MSRC is part of the defender community and on the front line of security response evolution. Our mission is to protect employees, customers, communities, and Microsoft from threats to privacy and security.

Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Minimum Qualifications:

• 5+ years experience in software development lifecycle, large-scale computing, modeling, cybersecurity, and/or anomaly detection.
  • OR Master's Degree in Statistics, Mathematics, Computer Science or related field.
• Track record of relevant research, as evidenced by high-quality research outputs (e.g., code and/or publications).
• Appropriate background and familiarity with recent research in security and privacy for AI systems
• Software development skills and experience.
• Creative and collaborative approach to problem-solving.

Other Requirements:

Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include, but are not limited to the following specialized security screenings:

Microsoft Cloud Background Check:

• This position will be required to pass the Microsoft background and Microsoft Cloud background check upon hire/transfer and every two years thereafter.

Preferred Qualifications:

• 6+ years experience in software development lifecycle, large-scale computing, modeling, cybersecurity, and/or anomaly detection.
  • OR Doctorate in Statistics, Mathematics, Computer Science or related field.
• Experience in other areas of security and privacy in addition to AI (e.g., web security, systems security, etc.).

Security Research IC4 - The typical base pay range for this role across the U.S. is USD $117,200 - $229,200 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $153,600 - $250,200 per year.

Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here: https://careers.microsoft.com/us/en/us-corporate-pay

Microsoft will accept applications for the role until May, 20, 2025.

#MSFTSecurity #MSRC #MSFTNSBE25

Research: The successful candidate will undertake research in the field of security and privacy for AI. Specific topics of interest include, but are not limited to:

• Investigating new security and privacy vulnerabilities in AI systems.
• Designing scalable mitigations for threats to AI systems, and working with product groups to drive these into product features.

Security Response: The successful candidate will work to assess reported security vulnerabilities in deployed AI systems, including:

• Analyzing and assessing the severity of reported vulnerabilities.
• Identifying new research opportunities based on vulnerability trends.

The successful candidate will collaborate cross-organizationally representing the One Microsoft model. They will work with security researchers and product groups to identify emerging threats to AI systems, and to design, implement, evaluate, and deploy mitigations for these threats. They will share their findings with security responders and product groups, as well as via publications in recognized academic venues.

Embody our culture and values.