What you will do

• Build AI-assisted research tools. Connect large language models (LLMs) and AI agents to code analysis and testing tools. Develop workflows that help researchers examine unfamiliar software, investigate suspected flaws, and test their reasoning against observed system behavior.
• Investigate complex software and systems. Use static and dynamic analysis techniques, such as source code review, binary reverse engineering, fuzzing, and debugging to assess applications, cloud services, and infrastructure. Identify security boundary failures and determine their underlying causes.
• Conduct original security research. Discover previously unknown vulnerabilities, including zero-days, and develop novel methods for investigating difficult targets. Explore emerging attack surfaces and potential new vulnerability classes as part of the broader research program.
• Validate findings and demonstrate impact. Create reproducible proofs of concept and controlled exploits that establish attack prerequisites and realistic consequences. Preserve the evidence needed for another researcher to reproduce and assess each result.
• Develop reusable research infrastructure. Automate target configuration and test execution, create fuzzing harnesses, and maintain shared analysis components. Make successful experiments repeatable across software versions and suitable for use by other researchers.
• Measure and improve research automation. Use benchmarks and independent checks to evaluate results. Study crashes, incorrect findings, and unsuccessful investigations to identify weaknesses in the workflow and guide improvements to its accuracy and coverage.
• Communicate research to stakeholders. Prepare technical briefings that explain findings, supporting evidence, and research limitations. Discuss open questions with stakeholders and identify opportunities for further investigation.
• Lead research projects. Choose promising investigations, define objectives, and manage technical uncertainty. Communicate progress and tradeoffs, adjust priorities as evidence develops, and deliver research results and tools aligned with organizational needs.
• Share expertise and strengthen the team. Review technical work, document research methods, and mentor colleagues. Contribute to technical publications, conference presentations, and open-source projects when appropriate and approved.

Required qualifications

• Relevant education and experience meeting one of the following combinations:

• Bachelor’s degree and 7 years of relevant experience.
• Master’s degree and 5 years of relevant experience.
• Doctorate and 3 years of relevant experience.
• 11 years of relevant experience without the degree combinations above.

Relevant fields include computer science, electrical engineering, cybersecurity, mathematics, or related disciplines. Relevant experience includes security research, security assessments, penetration testing, software engineering, software architecture, or related technical work.

• Demonstrated contributions to security research or research tooling, with the ability to explain your technical approach, individual contribution, and results. Evidence may include validated findings, analysis tools, technical reports, or comparable public or confidential work.
• Deep expertise in one or more areas such as binary analysis, application security, operating system security, cloud security, virtualization, network protocols, fuzzing, or program analysis.
• Strong programming skills for developing research tools and proofs of concept, including proficiency in a language such as Python and the ability to analyze code in languages relevant to your research area.
• Practical experience with debuggers, disassemblers, decompilers, instrumentation frameworks, or comparable tools, supported by a strong understanding of vulnerability classes, exploitation principles, and defensive mitigations.
• Ability to independently investigate ambiguous problems, design reproducible experiments, distinguish evidence from assumptions, and document limitations.
• Clear technical communication, effective collaboration with researchers and stakeholders, and sound judgment when handling sensitive findings and conducting authorized research.

Preferred qualifications

• Experience developing LLM-based research tools or AI agents that interact with code repositories, debuggers, analysis tools, and test environments.
• Experience creating evaluation datasets, automated validation systems, or benchmarks for security research automation.
• Experience discovering zero-day vulnerabilities or contributing novel security research methods, exploitation techniques, or insights into emerging attack surfaces.
• Experience analyzing native code and assembly, investigating memory corruption, or researching kernels, hypervisors, containers, and isolation boundaries.
• Experience supporting client-sponsored security research, presenting complex findings, and handling confidential technical information.
• Experience mentoring researchers or guiding investigations that advanced a team’s research methods or technical capabilities.