ServiceNow
Senior Staff ML Engineer, AI Safeguards - Moveworks
Mountain View, CALIFORNIA, United States · Senior Staff · Full-time · Posted Oct 28, 2026
- Experience
- Typically 8 or more years building production software, including 3 or more years of applied ML (training, evaluating and deploying models in production systems).
About the job
Build and operate AI safeguards that protect agentic AI systems from prompt injection, jailbreaks, harmful content, and sensitive data exposure.
What you'll do
- Design safeguards and evaluation datasets and metrics; integrate and fine-tune detection models.
- Partner with Security to convert adversarial findings into tests and mitigations, and balance quality, latency, and cost.
- Configure customer policies, monitor safeguards in production, and fix regressions.
What they ask for
- Hands-on experience developing LLM safeguards, such as guardrail models, content classifiers, prompt injection or jailbreak detection, or safety evaluations.
- Strong model evaluation fundamentals for agent trajectories and text classification, with attention to training and evaluation data quality.
- Working knowledge of safeguard bypasses, including indirect prompt injection and multi-turn jailbreaks.
- Excellent Python experience.
Tools
Python
AI focus
Develop, evaluate, integrate, and operate LLM safeguards, including detection models and configurable policies.
Model-written summary · the original posting is authoritative