ServiceNow
Senior Staff Security Engineer, AI Safeguards - Moveworks
Mountain View, CALIFORNIA, United States · Senior Staff · Full-time · Posted Oct 28, 2026
- Experience
- Typically 8 or more years in security engineering, including 2 or more years focused on AI or LLM security.
About the job
Leads security design and testing for AI/ML features, builds safeguards and mitigations, and measures their effectiveness against attacks on LLM systems.
What you'll do
- Maintain the map of ML usage and safeguards, and lead security design for new ML features.
- Test safeguards against attacks and convert findings into repeatable evaluations and mitigations.
- Define and report security metrics, review changes that could weaken safeguards, and track emerging AI attack research.
What they ask for
- Hands-on adversarial experience applied to LLM systems, such as red teaming, penetration testing, or vulnerability research.
- Deep knowledge of LLM attacks and defenses, including frameworks such as the OWASP Top 10 for LLM Applications and MITRE ATLAS.
- Strong Python or Go coding skills and a record of shipping production code.
- Ability to assess risks, implement fixes, and apply ML fundamentals to build evaluations and judge classifier efficacy.
Tools
Python, Go, OWASP Top 10 for LLM Applications, MITRE ATLAS
AI focus
Secures AI/ML and LLM features by adversarially testing safeguards, building evaluations and mitigations, and measuring safeguard effectiveness.
Model-written summary · the original posting is authoritative