Microsoft
Senior AI Security Researchers
$120K–$304K
Redmond, WA · On-site · Senior · Full-time · Posted Oct 23, 2026
- Experience
- Minimum: Master's degree plus 3+ years, or bachelor's degree plus 4+ years, in listed relevant fields; doctorate is an alternative. Preferred: doctorate plus 3+ years, master's plus 6+ years, or bachelor's plus 8+ years; also 6+ years in security research and/or AI/ML security.
- Education
- Doctorate or master's in Statistics, Mathematics, Computer Science, Computer Security, or related field; alternatively, bachelor's in these fields or equivalent experience.
About the job
Research and simulate attacks against AI systems, develop scalable red-teaming tools, and turn findings into defenses and product improvements.
What you'll do
- Design and execute AI attack simulations, evaluate defenses, and recommend mitigations.
- Build automated red-teaming tools and research emerging attacker techniques.
- Shape research methodology, mentor team members, and communicate findings to technical and executive audiences.
What they ask for
- Degree in Statistics, Mathematics, Computer Science, Computer Security, or a related field, or equivalent experience; minimum education and experience alternatives are specified.
- For the master's route, 3+ years of relevant experience; for the bachelor's route, 4+ years of relevant experience. Relevant areas include software development lifecycle, cybersecurity, threat analysis, vulnerability research, and anomaly detection.
- Ability to meet Microsoft, customer, and/or government security screening requirements, including a Microsoft Cloud Background Check.
Nice to have
- Security research and/or AI/ML security experience; practical security research, vulnerability exploitation, and hands-on AI attack experience.
- Python, agentic AI systems, red-teaming tools, AI security frameworks, and contributions to AI security research, publications, CTFs, or open-source.
Pay
USD $119,800 - $234,700 per year (base salary); USD $160,200 - $261,000 per year (base salary); USD $142,800 - $274,800 per year (base salary); USD $188,000 - $304,200 per year (base salary)
Tools
Python, LLMs, RAG, MITRE ATLAS, OWASP Top 10 for LLM Applications, LLM APIs
AI focus
Conduct offensive AI security research, including prompt injection, jailbreaks, data leakage, agent abuse, and model/data attacks; build evaluation tooling and develop defenses for AI systems.
Model-written summary · the original posting is authoritative