Overview of Role
In this role, you will manage multiple aspects of AI information security operations, response, and engineering with a specialized focus on securing AI/ML systems and infrastructure. This position will contribute to a team focusing on incident response, playbook development and execution, operational engineering, AI governance, tooling maintenance, and serving as a key participant in Information Security and AI governance programs. You will work in close collaboration with all IT and AI/ML teams to design and support effective Information Security Operations for International, with emphasis on emerging AI threats and generative AI security.
Responsibilities
• Manages and is responsible for the successful completion of all tasks in assigned projects.
• Contribute to the Security Operations and Engineering Team focused on maintaining the security integrity of the client's mission critical suite of applications.
• Available 24/7 for any critical security incident response that may arise which requires immediate resolution.
• Work to ensure security tooling within environments is operational and operating at needed levels of service and availability.
• Ensure operational practices provide a sound foundation that utilizes tools and processes for rapid identification of security events to address and mitigate risks.
• Assist in Plan, organize, and execute multiple responsibilities to achieve project goals and provide technical leadership to move operational projects to completion.
• Contribute to security requirements, standards, procedures, and reference architectures to comply with policies and technical standards.
• Develop and maintain incident response playbooks specific to AI/ML security threats including prompt injection, model poisoning, data exfiltration, and adversarial attacks.
• Monitor and secure generative AI systems, large language models (LLMs), and AI-powered applications within environments.
• Contribute to AI governance frameworks and policies ensuring responsible AI practices and compliance with AI-specific security standards.
• Analyze and evaluate security implications of new AI/ML tools and platforms before deployment to production environments.
• Participate in AI threat intelligence activities and stay current with emerging AI security vulnerabilities and attack methodologies.
• Conduct post-incident analysis for AI-related security events and develop preventive measures specific to AI threat vectors.
• Review and validate AI model security properties, including robustness against adversarial inputs and data privacy protections.
Qualifications
• Manages and is responsible for the successful completion of all tasks in assigned projects.
• Contribute to Security Operations and Engineering Team focused on maintaining the security integrity of mission critical suite of applications.
• Serve as a key engineering contributor for AI operations, building and maintaining the tooling, pipelines, and telemetry that support secure deployment of AI/ML systems.
• Work to ensure security tooling within environments is operational and operating at needed levels of service and availability.
• Engineer operational practices, tooling, and detection pipelines that provide a sound foundation for identifying and addressing AI/ML security events.
• Contribute to "Continuous Improvement and Posture Management" efforts, in respect to information security tooling, response playbooks, and systems.
• Assist in Plan, organize, and execute multiple responsibilities to achieve project goals and provide technical leadership to move operational projects to completion.
• Contribute to security requirements, standards, procedures, and reference architectures to comply with policies and technical standards.
• Engineer detection logic and playbooks specific to AI/ML security threats including prompt injection, model poisoning, data exfiltration, and adversarial attacks.
• Monitor and secure generative AI systems, large language models (LLMs), and AI-powered applications within environments.
• Contribute to AI governance frameworks and policies ensuring responsible AI practices and compliance with AI-specific security standards.
• Analyze and evaluate security implications of new AI/ML tools and platforms before deployment to production environments.
• Participate in AI threat intelligence activities and stay current with emerging AI security vulnerabilities and attack methodologies.
• Assist in configuration of AI/ML system telemetry and logging for comprehensive security event detection and forensic analysis.
• Review and validate AI model security properties, including robustness against adversarial inputs and data privacy protections.