Principal Engineer, AI Security

Granicus is a company focused on transforming the Govtech industry through technology that connects governments with their constituents. They are seeking a Principal Engineer in AI Security to lead the development of AI security capabilities and control planes, ensuring secure adoption of AI and defense against AI-enabled threats.

Responsibilities:

• Design and implement scalable controls for AI-enabled development and operations
• Establish secure patterns for: LLMs and agents, AI-assisted development, model and inference access, data protection and governance, AI telemetry and visibility
• Create guardrails that enable safe AI adoption without slowing engineering velocity
• Partner with Product Security and Engineering to evolve the SDLC for an AI-enabled world
• Embed security directly into developer workflows through: pipeline enforcement, AI-aware testing, secure coding patterns, and automated controls
• Help shift vulnerability management from reactive patching toward systemic risk reduction
• Partner with Cyber Defense teams to address how AI changes: attacker behavior, detection and response, vulnerability exploitation, and operational tempo
• Prototype and implement AI-enabled approaches for: detection engineering, prioritization, and security operations automation
• Translate emerging AI risks into actionable engineering strategy
• Identify high-risk gaps and drive practical solutions
• Establish scalable architectural and implementation patterns across teams
• Serve as a senior technical advisor across security and engineering organizations
• Prototype systems, controls, and integrations directly
• Evaluate emerging AI tooling, technologies, and attack techniques
• Contribute code, architecture, and technical designs where needed

Requirements:

• 10+ years of experience in Security Engineering, Product Security, Application Security, Platform Security, or related technical disciplines
• Experience operating as a senior or principal-level technical leader across multiple engineering domains
• Deep familiarity with LLMs, copilots, agents, AI-assisted development, and AI-enabled workflows
• Strong understanding of how AI changes SDLC practices, attack surfaces, vulnerability management, identity and access models, and security operations
• Actively builds and experiments with AI technologies
• Experience securing AI-enabled applications or platforms in production
• Familiarity with adversarial AI, prompt injection, model abuse, or AI red teaming
• Experience integrating security controls into large-scale engineering workflows
• SaaS, cloud-native, or regulated industry experience
• Strong background in cloud-native architectures, APIs and distributed systems, CI/CD and developer tooling, security automation, and secure software engineering
• Ability to design pragmatic, scalable security controls and patterns
• Builder mentality with strong systems-thinking capability
• Pragmatic, execution-oriented, and comfortable operating in ambiguity
• Able to influence teams without relying on formal authority
• Focused on solving real problems—not implementing theoretical framework