Senior Staff Security Engineer, AI Safeguards
ServiceNow15 hours ago
Responsibilities
- Maintain the map of ML usage and safeguards across products and lead security design for new ML features.
- Perform adversarial testing of jailbreaks, prompt injection, prompt leaks, toxicity, and related LLM threats.
- Convert security findings into evaluation cases that run across model, prompt, and safeguard changes.
- Design and build mitigations with ML engineers, including defenses that remain effective when detection misses.
- Define and report security metrics measuring safeguard effectiveness.
- Review changes that could weaken safeguards and track AI attack research to create new tests and mitigations.
Requirements
- Typically 8 or more years of security engineering experience, 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, including frameworks such as the OWASP Top 10 for LLM Applications and MITRE ATLAS.
- Ability to identify risks, develop mitigation plans, and implement fixes directly.
- Strong coding skills in Python or Go and a record of shipping production code.
- ML fundamentals sufficient to build evaluations and assess classifier efficacy.
Benefits
- Flexible or remote work persona, subject to eligibility based on assigned work location.
- Regular employee position in the AMS - North America and Canada region.
About ServiceNow
ServiceNow builds a cloud platform for enterprise digital workflows, covering IT service management, customer service, HR service delivery, security operations, and operations management, plus tools for custom app development. It sells subscription SaaS to large organizations and public-sector agencies to automate processes and connect data across systems. Founded in 2004 and headquartered in Santa Clara, California, ServiceNow is a public company listed on the NYSE under the ticker NOW.