Senior Staff Security Engineer, AI Safeguards - Moveworks
Core
Lead security design and adversarial testing for ML features and safeguards across the Agentic AI platform, ensuring robustness against attacks like jailbreaks and prompt injection.
Role type
Senior Staff Security Engineer (AI Safeguards)
Builds
Production ML safeguards, eval cases, and mitigation strategies for LLM systems.
Domain
AI Safety / LLM Security
Deliverable
production ML models
Required skills
Adversarial testing (red teaming, penetration testing), LLM attack/defense knowledge (OWASP Top 10 for LLM, MITRE ATLAS), Python or Go coding, ML fundamentals for eval design, risk identification and mitigation planning.
Preferred skills
Experience with agentic AI systems, deep knowledge of AI attack research trends.
Responsibilities
Maintain ML usage and safeguards maps, test boundaries for jailbreaks/prompt injection/toxicity, design mitigations for detection misses, define and report security metrics, review changes weakening safeguards, track AI attack research and implement tests.
Seniority
Senior Staff, hands-on IC
