AI Security Architect

At IRIUM we want you to always chase your dreams. Here, prepare yourself to conquer your goals, while enjoying the journey.

We are currently looking for: AI Security Architect.

Requirements:

At IRIUM, we help organizations embrace innovation securely by connecting them with top technology talent. We are looking for an experienced AI Security Architect to support and secure AI and Generative AI initiatives, ensuring that AI solutions are designed, implemented, and operated according to cybersecurity best practices. This is a cybersecurity role focused on AI/GenAI, supporting architecture, governance, and security validation rather than AI model development or data engineering.

Required Competencies:

• 5+ years of experience in Cybersecurity, Application Security, Product Security, Cloud Security, or Security Architecture.
• Strong understanding of Generative AI / LLM-based solutions from a security and risk perspective.
• Experience supporting and reviewing AI/GenAI use cases from design through production.
• Experience performing architecture reviews, security reviews, and threat modelling.
• Ability to define security requirements for AI platforms, APIs, agents, tool usage, and integrations.
• Experience with IAM, API Security, Secrets Management, Logging, Monitoring, and Security Control Validation.
• Strong knowledge of data protection, privacy, data minimization, and secure handling of sensitive or regulated data.
• Experience identifying and mitigating AI-specific risks, including:
  • Prompt Injection and Jailbreak attacks;
  • Sensitive information disclosure and data leakage;
  • Unsafe tool usage and excessive agent autonomy;
  • Abusive or unbounded AI consumption;
  • Insecure integrations and poisoned inputs.
• Experience defining AI guardrails and secure-by-design architectures.
• Ability to validate security controls, auditability, logging, and monitoring requirements.
• Strong communication skills and ability to work with Security, Engineering, Product, and Data teams.
• English C1 or above.

Preferred Competencies:

• Experience with AWS and/or Azure environments.
• Experience with AWS Bedrock, Azure OpenAI, Azure AI Foundry, or similar GenAI platforms.
• Knowledge of AI Guardrails, IAM, Least Privilege, Observability, Auditability, and Data Protection.
• Experience reviewing Databricks environments from a security perspective.
• Familiarity with:
  • OWASP Top 10 for LLM Applications / Agentic AI;
  • Secure AI Framework (SAIF);
  • Model Context Protocol (MCP);
  • Agent-to-Agent (A2A) architectures;
  • MCP-38 and emerging AI security risk taxonomies;
  • Exposure to DevSecOps and/or MLOps environments.

Location:

Portugal – Hybrid.

Gross Salary Range:

5,143€–5,429€.