SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
ServiceNow is seeking a Principal AI Security Engineer to own the security strategy and architecture for the company's Agentic AI ecosystem, LLMs, and models across product lines. This is a hands-on architecture role combining deep research, secure systems design, and prototyping with minimal direction and broad latitude to set the technical agenda.
You will set platform-wide direction for securing the AI development lifecycle, define the security architecture for agents and models operating within it, and represent ServiceNow's AI security perspective externally to standards bodies, industry publications, and conferences. You'll be a technical authority that other engineers and teams consult on emerging AI-specific threats, working closely with the AI security research team to draw on their findings and feed real-world attack surfaces back into their research agenda.
Key responsibilities include:
- Owning the security strategy and architecture for the Agentic AI ecosystem, LLMs, and models across product lines
- Leading threat modeling for complex and novel GenAI/agentic surfaces, including cross-agent autonomy, multi-agent tool orchestration, and emerging attack classes not yet standardized in the industry
- Setting the architectural standard for securing model/RAG/data pipelines platform-wide, including access-control and data-boundary models that other teams build against
- Defining what "secure-by-design" means for agentic systems at ServiceNow and driving adoption across engineering organizations
- Representing ServiceNow's AI security posture externally and internally to executive stakeholders
- Mentoring and technically guiding engineers on AI-specific security work
REQUIREMENTS:
- Bachelor's, Master's degree, or PhD in Computer Science or related technical field with specialization in Security or AI/ML (or exceptional, well-evidenced track record substituting for it)
- 10+ years of software engineering experience, including a track record of owning the architecture of complex systems at enterprise scale
- Track record of setting technical direction beyond your own team—architecture or standards other teams adopted, senior engineers you've leveled up, and comfort operating where the problem isn't yet defined
- 7+ years in security engineering (network and systems security, security protocols, design reviews, threat modeling) with focus on AI-specific work in recent years
- Multiple demonstrated engagements threat modeling and/or securing LLM, GenAI, or agentic systems, with evidence of platform-level or cross-team impact
- Personal ownership of prompt injection/jailbreak defense, guardrail architecture, or AI red-teaming programs—ideally having built the program/methodology, not just executed within one
- Deep, applied experience securing model, RAG, or data pipelines, including having designed the access-control and data-governance model others build against
- Fluency with the OWASP LLM Top 10 (or equivalent) to the point of extending, critiquing, or contributing to such frameworks—not just applying them
- Deep hands-on experience with agentic AI frameworks (e.g., LangChain, LangGraph)
- Clear communication, collaborative default, and bias toward learning fast in a constantly changing field
BONUS QUALIFICATIONS:
- Strong command of auth protocols (OAuth 2.0, OIDC, PKCE, API Keys) and agentic protocols (MCP, A2A), including having designed identity/consent models for them
- Built and open-sourced (or productized) security tooling/automation for AI systems used beyond one team
- Track record of CVEs, top-tier publications, or invited talks specifically in AI/ML or LLM security
- Prior experience setting AI security strategy at a platform or company level, not just a single product
- 5+ years of programming experience in Java or Python
