About the Role

The Security Researcher II role focuses on offensive security operations and research for Microsoft 365 Copilot AI products. Responsibilities include identifying AI security threats, performing penetration testing, and developing tools to exploit vulnerabilities. The position requires expertise in AI/ML security, Python, and offensive security techniques.

Key Responsibilities

• Research emerging AI security threats and attack techniques
• Design and implement AI agent security testing methodologies
• Execute penetration tests on AI platforms focusing on prompt injection and jailbreaking
• Develop proof-of-concept exploits for identified vulnerabilities
• Create AI security testing frameworks and automated validation tools

Required Skills & Qualifications

Must Have:

• Bachelor's Degree in Statistics, Mathematics, Computer Science or related field OR 3+ years experience in software development lifecycle, large-scale computing, modeling, cybersecurity, and/or anomaly detection
• 3+ years of experience in security research, penetration testing, or offensive security roles with demonstrated expertise in AI/ML security
• Strong understanding of AI attack vectors including prompt injection, agent manipulation, and workflow exploitation
• Hands-on experience discovering and exploiting vulnerabilities in AI systems and platforms

Nice to Have:

• Direct experience testing AI agent platforms, conversational AI systems, or AI orchestration architectures
• Published security research or conference presentations on AI security topics
• Background in software engineering with distributed systems expertise
• Security certifications such as OSCP, OSCE, GPEN, or similar
• Knowledge of AI agent communication protocols and multi-agent architectures

Benefits & Perks

• Industry leading healthcare