Staff AI Security Engineer

What you'll do

• Develop and own the multi-year AI and agentic security roadmap, including vision, strategy, and standards.
• Secure the inference and agent stack by implementing controls against prompt injection, jailbreaking, and data poisoning.
• Define security requirements for MCP server registration, tool authentication, and agent-to-tool trust boundaries.
• Establish and execute AI red-teaming and adversarial testing to identify failure modes before production.
• Create assessment frameworks using OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF.
• Build automated security tools and policy-as-code for the gateway to ensure scalable, secure-by-default systems.
• Partner with platform engineering teams to embed security controls directly into the infrastructure layer.

What we're looking for

• Experience in security engineering within the software development lifecycle, including design, code review, CI/CD, and production.
• Hands-on experience with AI/LLM and agentic security, specifically regarding prompt injection, jailbreaking, and data poisoning.
• Working knowledge of AI-specific frameworks such as OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF.
• Experience securing infrastructure like API gateways, agent orchestration platforms, or MCP/tool-registry architectures.
• Familiarity with LLM red-teaming tools (e.g., Garak, PyRIT) and evaluation/observability platforms.
• Proven track record of defining multi-year security strategies and building scalable automation and tooling.
• Proficiency in modern cloud infrastructure (AWS, GCP, or Azure) and CI/CD pipelines.
• Solid coding skills in a modern programming language such as Python or Go.