AI Security Engineer, AI Security Unit
Check Point Software Technologies5 hours ago
Responsibilities
- Deliver AI red teaming security assessments for enterprise customers.
- Scope projects with clients, define testing requirements, and establish success criteria.
- Assess text-based LLM applications, multimodal agentic systems, connected tools, APIs, and services.
- Perform creative manual testing alongside automated testing to identify vulnerabilities.
- Write security assessment reports with actionable findings and remediation recommendations.
- Present findings and strategic recommendations to technical and executive stakeholders.
- Develop AI red teaming frameworks, methodologies, playbooks, documentation, and automation.
- Research emerging AI security threats, attack vectors, defense mechanisms, and modalities.
- Collaborate with research and product teams to improve AI security methodologies.
Requirements
- Demonstrated offensive security experience through red teaming, penetration testing, security assessments, bug bounty programs, and/or CTF participation.
- Ability to manually identify and exploit real vulnerabilities, beyond operating automated tools.
- Strong knowledge of web application, API, and network security fundamentals.
- Deep understanding of LLM vulnerabilities, including prompt injection, jailbreaking, data poisoning, agentic risks, and tool-use risks.
- Practical experience threat-modeling complex systems and architectures.
- Proficiency developing automated tooling to improve testing capabilities and workflows.
- Experience contributing to or leading client-facing security assessment projects from scoping through delivery.
- Excellent technical writing, reporting, presentation, and customer communication skills.
- Understanding of AI/ML model architectures, training processes, and deployment patterns.
- Familiarity with OWASP Top 10 for LLM Applications, OWASP Top 10 for Agentic Applications, and MITRE ATLAS.
- Knowledge of multimodal systems, AI agents, and tool and Model Context Protocol integrations.
- Preferred qualifications include relevant security certifications such as OSCP, OSWA, OSAI, COAE, or BSCP.
- Preferred qualifications include professional penetration testing, AI red teaming, LLM jailbreak design, security research, threat modeling, risk assessment, or security conference speaking experience.
Benefits
- Opportunity to shape the future of AI security and work with emerging AI technologies and attack methodologies.
- Lead high-visibility projects with enterprise clients across diverse industries.
- Collaborate with a research team focused on AI safety and receive research and development time between engagements.
- Build thought leadership within the AI security community.
- California, US remote work arrangement.
Categories
About Check Point Software Technologies
Check Point Software Technologies Ltd. is a leading protector of digital trust, utilizing AI-powered cyber security solutions to safeguard over 100,000 organizations globally. Through its Infinity Platform and an open garden ecosystem, Check Point’s prevention-first approach delivers industry-leading security efficacy while reducing risk. Employing a hybrid mesh network architecture with SASE at its core, the Infinity Platform unifies the management of on-premises, cloud, and workspace environments to offer flexibility, simplicity and scale for enterprises and service providers.