AI Security Engineer — Red Team & AI Defense

Check Point Software; Seattle (WA); On-site; USD 180,000 - 240,000; Full time

Job summary

Check Point Software in Seattle is seeking an AI Security Engineer to join our Red Team and advance AI security testing for enterprise clients. You will conduct cutting-edge security assessments of AI systems, including LLMs and multimodal agents, and develop scalable testing frameworks.

The role blends hands-on red teaming with automation, client engagement, and collaboration with research and product teams to push the boundaries of AI safety and secure deployment across industries.

Qualifications

• Proven offensive security experience through red teaming and security assessments.
• Ability to manually identify and exploit real vulnerabilities.
• Solid grasp of web, API, and network security fundamentals.
• Deep understanding of AI/LLM vulnerabilities and prompt techniques.
• Experience with threat modeling for complex systems and architectures.
• Ability to build automated tooling to scale testing and insights.

Responsibilities

• Deliver AI red teaming security assessments for enterprise customers.
• Define testing requirements and success criteria with clients.
• Assess AI systems including text-based LLM applications and multimodal agents.
• Extend tests to tools, APIs, and services connected to AI systems.
• Combine manual testing with automation and produce detailed reports.
• Present findings and strategic recommendations to technical and executive stakeholders.

Skills

Offensive security

Manual pentesting

Web/API security

LLM vulnerabilities

Threat modeling

Automation tooling

Job description

Check Point Software in Seattle is seeking an AI Security Engineer to join our Red Team and advance AI security testing for enterprise clients. You will conduct cutting-edge security assessments of AI systems, including LLMs and multimodal agents, and develop scalable testing frameworks.

The role blends hands-on red teaming with automation, client engagement, and collaboration with research and product teams to push the boundaries of AI safety and secure deployment across industries.