AI Penetration Tester - Cybersecurity Team

The Trust and Integrity Protection (TrIP) team supports the company’s overall security and privacy mission by providing key security services that help protect systems, services, data.  

Are you passionate about identifying security vulnerabilities and risks in enterprise-scale systems with specific focus on Artificial Intelligence? Do you want the challenge of conducting penetration tests against some of the world’s most cutting-edge technology implementations? Are you a red teamer and interested in Artificial intelligence (AI) and excited about technology like GPT4? Do you want to find and exploit security vulnerabilities in Microsoft’s largest AI systems impacting millions of users?  

The TrIP Offensive Cyber Security Team is an interdisciplinary group of  internal penetration testing and offensive security team, tasked with identifying security flaws across the entire Microsoft Customer and Partner Solutions (MCAPS) technology estate. 

We are looking for an AI Penetration Tester - Offensive Cybersecurity Team to help make AI security better.   

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. 

Required Qualifications

• Bachelor's Degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, PowerShell or Python
  • OR equivalent experience.
• 4+ years experience in identifying security vulnerabilities, software development lifecycle, large-scale computing, modeling, cyber security, and anomaly detection.
• 4+ years of experience of using common penetration testing tools; Kali Linux, Burpsuite, Nmap, Nessus, etc.

Preferred Qualifications

• Bachelor's Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python

  • OR Master's Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python

  • OR equivalent experience.
• Penetration testing qualifications; PNPT, GPEN/GXPN, GWAPT, OSCP/OSCE, CRT/CCT/CCSAS and/or equivalent.
• Familiarity with MITRE ATLAS/OWASP top 10 LLMS.
• Proficient in developing novel tooling and techniques, as well as utilizing existing methodologies, should consistently explore possibilities and persistently push the boundaries.

Software Engineering 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:

Microsoft will accept applications and processes offers for these roles on an ongoing basis.

#EDOTjobs

• Discover and exploit vulnerabilities end-to-end in order to assess the security of AI systems 

• Execute offensive operations on production AI systems using real world adversarial tactics and techniques to identify failures 

• Develop tools and techniques to scale and accelerate offensive emulation and vulnerability discovery specific for AI systems 

• Collaborate with teams to influence measurement and mitigations of these vulnerabilities in AI systems 

• Research new and emerging threats to inform the organization including prompt injection, improve red teaming efficacy and accuracy, and stay relevant. 

• As an AI Penetration Tester for TrIP’s Offensive Cybersecurity Team, you will discover and exploit vulnerabilities end-to-end in order to assess the security of AI systems. 

• Execute Penetration Testing operations on production AI systems using real world adversarial tactics and techniques to identify failures. 

• The candidate who is well-suited for this role will possess solid technical skills, coupled with a passion for identifying security flaws and developing innovative solutions. 

• Develop tools and techniques to scale and accelerate offensive emulation and vulnerability discovery specific for AI systems. 

• Perform research to stay current with penetration testing tools, methodologies, tactics, and mitigations. 

• Develop, operationalize and maintain penetration testing procedures and methodologies. 

• Produce high-quality papers, presentations, as well as recommendations to key stakeholders. 

• Research new and emerging threats to inform the organization, improve red teaming efficacy and accuracy, and stay relevant. 

• Team up with other Offensive Security personnel at Microsoft to leverage the latest trends, and identify good opportunities for attack. 

• Discovery of Problems/Identifying Vulnerabilities in Generative AI and AI systems. 
• Regularly assess security, identify and fix vulnerabilities, create threat models, review code for security flaws, and perform security tests (SAST, DAST, IAST) to uncover application vulnerabilities.

• Embody our and .