AI Security Red Team Engineer

Check Point Software Technologies Ltd.; Austin (TX); On-site; USD 140,000 - 210,000; Full time

Job summary

Check Point Software Technologies Ltd. is seeking an AI Security Engineer to join our Red Team and advance AI security assessments for enterprise customers.

You will run cutting-edge tests, develop novel methodologies, and collaborate directly with clients to define scope and success criteria. This role blends hands-on red teaming with automation development, enabling scalable security testing of AI systems across text and multimodal interfaces.

Qualifications

• Offensive security experience through red teaming, pentesting, or bug bounty programs.
• Ability to find and exploit real vulnerabilities by hand, not only using tools.
• Strong knowledge of web, API, and network security fundamentals.
• Deep understanding of LLM vulnerabilities and prompt-related risks.
• Experience with threat modeling complex systems and architectures.
• Proficiency in developing automated tooling to enhance testing workflows.

Responsibilities

• Deliver AI red teaming security assessments for enterprise customers.
• Collaborate with clients to scope projects and define testing requirements.
• Conduct comprehensive security assessments of AI systems, including LLMs and multimodal agents.
• Extend testing to tools, APIs, and services these AI systems connect to.
• Develop frameworks and playbooks to scale service delivery.
• Build automated tools to automate routine testing tasks.

Skills

Red teaming

Vulnerability assessment

Manual testing

Threat modeling

AI/LLM security

Automated tooling

Job description

Check Point Software Technologies Ltd. is seeking an AI Security Engineer to join our Red Team and advance AI security assessments for enterprise customers.

You will run cutting-edge tests, develop novel methodologies, and collaborate directly with clients to define scope and success criteria. This role blends hands-on red teaming with automation development, enabling scalable security testing of AI systems across text and multimodal interfaces.