AI Security Engineer – Generative AI

About the role

IRIUM is seeking an AI Security Engineer to protect and govern our Generative AI solutions. You will work closely with product security, engineering, and data teams to embed security throughout the AI lifecycle, from design to production.

Key responsibilities

• Support and review AI/GenAI use cases from design through deployment.
• Define security requirements for AI platforms, APIs, agents, and integrations.
• Perform architecture and security reviews of AI solutions.
• Validate integrations and deployments against security requirements.
• Identify and mitigate risks such as prompt injection, data leakage, model misuse, and abuse.
• Define guardrails for sensitive or regulated data usage.
• Ensure logging, monitoring, and auditability of AI usage.
• Contribute to AI governance and security standards.

Required profile

• Background in application, cloud, or architecture security.
• Understanding of Generative AI / LLM‑based solutions.
• Experience conducting security reviews and defining technical controls.
• Knowledge of data protection and privacy principles.

Required skills

• AWS
• Azure
• AWS Bedrock (or similar GenAI platforms)
• Databricks (securing ML workflows, notebooks, jobs, access control, data permissions)
• OWASP Top 10 for LLMs / Agentic AI
• Secure AI Framework (SAI)
• Model Context Protocol (MCP‑38)
• Agent‑to‑Agent (A2A) architectures
• DevSecOps
• MLOps

What we offer

• Innovative, growing company with strong professional development opportunities.
• Compensation aligned with experience and performance, including flexible pay and medical insurance.
• Unlimited access to technological training.
• Dynamic, proactive work environment that values responsibility and quality.