As Microsoft continues to push the boundaries of AI, we are on the lookout for passionate individuals to work with us on the most interesting and challenging AI questions of our time. Our vision is bold and broad — to build systems that have true artificial intelligence across agents, applications, services, and infrastructure. Security Engineering for Copilot is focused on building and securing systems that accelerate this process by making it easy and safe to incorporate more data and functionality that would otherwise be too scary/risky to do. We are looking for a Principal Software Engineer to identify areas of risk and opportunity, then design and build solutions in Copilot, making the product and its platform more secure. This can include everything from secure coding standards, to API design, to infrastructure, sandboxing, automated testing/fuzzing, application security, insider risk and abuse detection. Since Agential AI orchestration poses novel threats to security and privacy from information flows, misinterpretation, and exfiltration risk, you will be expected to have an understanding of these and be able to apply (or invent!) the latest research directly into the codebase to address these challenges. You will possess a methodical approach to problem-solving, proficiency in backend technologies, a familiarity with applied AI and its unique security challenges, and the ability to architect solutions that stand the test of time. Many problems in this space have not been solved before! The right candidate is hands-on and enjoys building world-class consumer experiences and products in a fast-paced environment. A key skill is the judgment to make the right risk vs velocity and value decisions.