Microsoft Senior AI Security Researcher 

Taiwan, Taoyuan City 

823473762

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.).

Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here:

Microsoft will accept applications for the roleuntil May, 20, 2025.

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.

Embody our and