Ai Security / Genai

IRIUM Portugal; Lisboa; Híbrido; EUR 90 000 - 130 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Medical insurance

Flexible pay

Professional development

Tech training

Resumo da oferta

IRIUM Portugal is seeking an AI Security professional to shape security for GenAI initiatives from design to production. You will translate risk into concrete technical requirements and work closely with Product Security and engineering teams to enforce controls.

Focus areas include data protection, guardrails for sensitive data, and auditable AI usage. This hybrid Lisbon-based role offers opportunities for professional development, flexible pay options, and medical insurance as part of the

Qualificações

• Background in security (application, cloud, or architecture).
• Understanding of GenAI / LLM-based solutions.
• Experience with security reviews and defining technical controls.
• Knowledge of data protection and privacy principles.

Responsabilidades

• Review AI/GenAI use cases from design to production.
• 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.
• Define guardrails for data usage, especially for sensitive data.
• Ensure logging, monitoring, and auditability of AI usage.

Conhecimentos

Security reviews

Risk assessment

Policy enforcement

Cross-functional collaboration

Technical communication

Ferramentas

Databricks

AWS Bedrock

OWASP

Descrição da oferta de emprego

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 / GenAI Requirements:

Key Responsibilities

• Support and review AI/GenAI use cases from design to production
• Define security requirements for AI platforms, APIs, agents, and integrations
• Perform architecture and security reviews of AI solutions
• Validate integrations and deployments of AI solutions against security requirements
• Identify and mitigate risks such as: Prompt injection / jailbreaks Data leakage / exposure Model misuse or abuse
• Define guardrails for data usage, especially for sensitive or regulated data
• Ensure logging, monitoring, and auditability of AI usage
• Contribute to AI governance and security standards
• Work closely with Product Security and engineering teams to enforce controls

Required Experience

• Background in security (application, cloud, or architecture)
• Understanding of GenAI / LLM-based solutions
• Experience with security reviews and defining technical controls
• Knowledge of data protection and privacy principles

Preferred Experience

• Familiarity with AWS and/or Azure environments
• Experience with AWS Bedrock or similar GenAI platforms
• Experience with Databricks, including securing: ML workflows and pipelines Notebooks and jobs Access control and data permissions
• Familiarity with: OWASP Top 10 for LLMs / Agentic AI SAIF (Secure AI Framework) Model Context Protocol (MCP), including MCP-38 Agent-to-Agent (A2A) architectures
• Exposure to DevSecOps / MLOps

Core Skills

• Can translate security into clear technical requirements
• Strong risk identification and prioritization
• Able to challenge and validate implementations effectively
• Works well with security, engineering, and data teams
• Focused on practical, enforceable controls

Location: Lisboa, hybrid

What do we offer?

• An innovative and growing company, with a lot of opportunities for professional development.
• Retribution according to your experience and performance.
• Access to flexible pay and medical insurance as a social benefit.
• Unlimited access to technological training in free mode.
• IRIUM is a company with dynamic and proactive professionals.
• Our values are responsibility and commitment to work quality.
• This is the spirit we are looking for at IRIUM, whatever your age is.
• If you recognize yourself in this, this is your company!
• We can build the future together.

At IRIUM we defend a world without stereotypes or limitations and we believe in equality for all, principles that we subscribe to in our Equality Plan and Code of Ethics, guaranteeing equal treatment and opportunities regardless of any personal, physical or social condition.