> Markdown version of [/jobs/ext/4721768-senior-staff-security-engineer-ai-safeguards-moveworks](https://www.wearedevelopers.com/jobs/ext/4721768-senior-staff-security-engineer-ai-safeguards-moveworks). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Senior Staff Security Engineer, AI Safeguards - Moveworks

- **Company:** ServiceNow
- **Location:** Mountain View, CA, United States (Remote available)
- **Experience:** Expert
- **Salary:** $201,300
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Software System Penetration Testing, Python (Programming Language), Open Web Application Security, Large Language Models, Build Management, Production Code, Software Coding, Servicenow, Vulnerability Analysis
- **Published:** November 14, 2026
- **Apply:** https://jobs.smartrecruiters.com/ServiceNow/744000161586589-senior-staff-security-engineer-ai-safeguards-moveworks

## About the Role

* Typically 8 or more years in security engineering, including 2 or more years focused on AI or LLM security
 * Hands-on adversarial experience, such as red teaming, penetration testing or vulnerability research, applied to LLM systems
 * Deep knowledge of LLM attacks and defenses (for example, the OWASP Top 10 for LLM Applications and MITRE ATLAS)
 * Ability to identify risks, develop mitigation plans, and implement the fixes yourself
 * Strong coding skills in Python or Go, and a record of shipping production code, not only findings
 * Enough ML fundamentals to build evals and judge the efficacy of a classifier

## Description

* Keep the map of ML usage and safeguards across our products current, and lead the security design of new ML features
 * Break our safeguards: test the boundaries on jailbreaks, prompt injection, prompt leaks and toxicity, and turn findings into eval cases that run on every model, prompt and safeguard change
 * Design and build mitigations with ML engineers that hold when detection misses
 * Define the security metrics that show whether our safeguards work, and report on them
 * Review changes that could weaken a safeguard
 * Track AI attack research and turn new techniques into tests and mitigations, We approach our distributed world of work with flexibility and trust. Work personas (flexible, remote, or required in office) are categories that are assigned to ServiceNow employees depending on the nature of their work and their assigned work location. Learn more here. To determine eligibility for a work persona, ServiceNow may confirm the distance between your primary residence and the closest ServiceNow office using a third-party service.