AI Security Specialist

About the Role

Responsibilities

• Define and maintain the AI security strategy across infrastructure and product ecosystems.
• Lead threat modeling and security assessments for AI/ML models, LLM integrations, and agentic systems.
• Evaluate and deploy AI Security Posture Management and AI Detection & Response solutions.
• Secure Model Context Protocol servers through authentication, authorization, data-flow controls, and supply-chain assessments.
• Own internal AI tool reviews, approvals, onboarding, and security guardrails.
• Develop policies for safe use of LLMs, AI code generators, and AI-powered SaaS.
• Harden AI-assisted development environments, application security reviews, CI/CD pipelines, and dependencies.
• Execute penetration tests covering prompt injection, model manipulation, data extraction, and adversarial attacks.
• Implement AI-environment DLP controls, including tenant restrictions, data classification, and prompt-injection mitigations.
• Review AI connectors, plugins, and third-party integrations.
• Build AI-specific detection rules, playbooks, and response procedures with SOC and incident response teams.
• Monitor emerging AI attacks and align controls with SOC 2 Type II, ISO 27001, GDPR, and other requirements.

Workplace

• The role offers flexibility of remote work, including optional WeWork access.

Compensation

• Salary ranges are quoted in USD as a consistent global reference and localized to the worker's country currency.
• Final pay is based on objective, job-related criteria including experience, skills, and location.

Benefits

• Stock grant opportunities and additional perks may depend on role, employment status, and location.

Requirements

• Ability to lead security assessments and threat modeling for AI/ML models, LLM integrations, and agentic AI systems.
• Ability to evaluate and approve AI tools, workflows, connectors, plugins, and third-party integrations using security controls.
• Knowledge of application security reviews, CI/CD pipeline hardening, and dependency scanning for AI-assisted development.
• Ability to plan and execute penetration testing against AI-powered systems, including prompt injection, model manipulation, data extraction, and adversarial attacks.
• Knowledge of AI-related DLP controls, data classification, tenant restrictions, and prompt injection mitigations.
• Ability to align AI deployments with SOC 2 Type II, ISO 27001, GDPR, and other regulatory requirements.