Microsoft Principal Security Researcher 

United States 

620766822

In this role, you will leverage LLMs and agentic systems to uncover and operationalize new adversarial techniques while addressing gaps in red team capabilities and supporting autonomous red team campaigns. You will use various approaches, including the analysis of structured and unstructured data such as code repositories and operational data, to identify new capabilities, assess design flaws and vulnerabilities, and expand our TTP catalog. You will also prototype and validate exploitation methods while helping design LLM-based workflows for TTP discovery and operationalization, advancing offensive data analysis and strengthening red team strategies.

Required/Minimum Qualifications

• 7+ 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.
• 7+ years experience as a red team operator with hands-on engineering expertise in developing custom tooling for adversary simulations and executing red team campaigns
• 5+ years experience proficiency as a reverse engineer and vulnerability researcher
  • With or without: exploit development experience, including analyzing artifacts collected during campaigns, researching scoped targets, debugging binaries, and identifying exploitable flaws.

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 Cloud background check upon hire/transfer and every two years thereafter.

Additional or Preferred Qualifications

• 8+ 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.
• Hands-on experience with Azure, AWS, and GCP environments.
• Proficiency in coding with languages such as C++, C#, Python, Go, and PowerShell.
• Verbal and written communication skills with the ability to convey complex security concepts effectively.
• Previous project management skills with a proven track record of driving projects to completion.

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

• Collaborate with the MS Red Team and Applied Research Scientists to leverage AI-driven techniques, including LLMs and agentic systems, to identify and operationalize new adversarial techniques, address capability gaps in red team engagements, expand the internal TTP catalog, and support autonomous red team campaigns.
• Design and implement data pipelines to analyze structured and unstructured data, create workflows for the identification and operationalization of adversarial techniques, and enrich operational data to generate actionable insights.
• Prototype, validate, and refine exploitation methods, using LLMs and agentic systems to discover vulnerabilities, develop exploits, and enhance workflows that automate and strengthen red team operations.
• Design and execute realistic attack simulations to test and improve methodologies, advancing offensive data analysis and supporting autonomous red team strategies.
• Cultivate global collaborations with security researchers to exchange knowledge, stay updated on emerging threats, and build partnerships with offensive security researchers to advance and integrate cutting-edge offensive security research shared within the community.
• Share knowledge with the community through presentations, publications, and active participation in social media, contributing to the broader information security ecosystem.

Other

• Embody our and