Information Security Engineer (AI Security) | 1

Job Description

We are looking for an experienced Information Security Engineer with a focus on AI Security to help ensure the secure, scalable, and compliant use of AI technologies across the organization.

In this role, you will define security guardrails, perform risk assessments and red-team exercises, and support AI solutions throughout their entire lifecycle: from design and development to production operations. Working closely with Security, Architecture, Engineering, Data Protection, Compliance, and Governance teams, you will play a key role in enabling the safe adoption of AI technologies, including machine learning models, Generative AI, agentic systems, and third-party AI services.

Main Tasks

• Perform threat modeling and security assessments for AI systems, including LLMs, GenAI solutions, agentic AI, and RAG architectures.
• Identify, assess, and mitigate AI-specific risks such as prompt injection, data poisoning, model leakage, and other emerging threats.
• Evaluate supply chain risks related to models, agents, plugins, and external AI services.
• Define and implement AI security guardrails, including input/output controls, security policies, rate limiting, monitoring, and isolation mechanisms.
• Establish and maintain security standards and best practices for production AI environments.
• Promote secure-by-design and privacy-by-design principles within AI architectures and development processes.
• Conduct security reviews and approval processes before AI solutions are deployed to production.
• Plan and execute AI-focused red-team and adversarial testing activities.
• Assess agentic workflows, automated execution mechanisms, and related abuse or privilege escalation risks.
• Define logging, monitoring, alerting, and incident response approaches for AI-based systems.
• Support investigations, incident response activities, and forensic analysis involving AI technologies.
• Collaborate with cross-functional stakeholders to ensure security, compliance, privacy, and governance requirements are met.
• Advise engineering and product teams on the secure implementation and operation of AI solutions.
• Contribute to AI security awareness and enablement initiatives across the organization.

Qualifications

• Several years of experience in Information Security, Cybersecurity, Application Security, Product Security, or a related field.
• Strong understanding of AI security concepts and risks.
• Knowledge of the OWASP LLM Top 10.
• Hands-on experience with threat modeling, security assessments, architecture reviews, and design reviews.
• Experience defining and implementing enterprise security controls.
• Experience working with audit logging, monitoring, and security observability solutions.
• Strong stakeholder management and communication skills, with the ability to collaborate across technical and non-technical teams.
• Experience supporting security processes throughout the software or AI system lifecycle.
• Fluent communication skills in English and Polish (minimum B2 level), both written and spoken.
• Availability to participate in a paid on-call duty rotation as part of the Security team operations.

Nice to Have

• Knowledge of the EU AI Act and other relevant regulatory frameworks.
• Experience implementing secure-by-design and privacy-by-design initiatives.
• Familiarity with agentic AI systems and Retrieval-Augmented Generation (RAG) architectures.
• Experience with model governance and AI supply chain security.
• Experience designing or delivering AI security awareness and AI literacy programs.
• Hands-on experience with AI security testing frameworks and adversarial testing techniques.

Additional Information

This position offers a hybrid or remote work model. Office locations for hybrid work: Warszawa, Poznań, Lublin

We hereby inform you that Inetum Polska sp. z o.o. has implemented an internal reporting (whistleblowing) procedure. The content of the procedure and the possibility to submit an internal report are available at:

https://inetum.whispli.com/speakup?locale=pl