Back to SearchSenior AI Security Engineer
Remote in Czech Republic
Security.Engineering
Looking for something else?
Find a vacancy that works for you. Send us your CV to receive a personalized offer.
Find me a job
We are building a unified, scalable AI security testing and benchmarking platform deeply integrated within the client’s Security ecosystem. This platform plays a critical role in evaluating AI usage monitoring at runtime to continuously validate AI agents and their embedded capabilities before adoption — ultimately reducing security, compliance, and remediation exposure across the client’s software delivery.
Responsibilities
- Design, build, and scale automated AI security testing and benchmarking pipelines within the client’s Security ecosystem
- Evaluate and implement runtime AI usage monitoring to continuously assess AI agents and their embedded capabilities prior to production adoption
- Conduct dynamic and static testing against AI architectures (including MCP, LLMs, and RAG pipelines) to uncover vulnerabilities aligned with the OWASP Top 10 for LLMs and Web Applications
- Partner closely with engineering, core security teams, and stakeholders to align on security guardrails, write clear technical documentation, and report on security posture and testing metrics
Requirements
- Solid foundation in security engineering principles, secure software development, and integrating security practices throughout the delivery lifecycle
- Deep grasp of application security fundamentals, secure architectures, and vulnerability management — including familiarity with web application threats and the OWASP Top 10 (Web, LLM, and MCP)
- Comprehensive, up-to-date understanding of AI security paradigms, architectures, and threat models, specifically concerning Model Context Protocol (MCP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG)
- Practical knowledge of both dynamic (DAST) and static (SAST) testing techniques to uncover and validate security flaws
Nice to have
- Basic ability to read code across multiple languages to understand functionality and implement small patches when needed
- Genuine interest in exploring the intersection of AI for security and security for AI
- Clear technical writing and reporting skills, with the ability to bridge technical concepts for non-technical stakeholders
- Experience driving cross-team alignment across engineering, security, and product groups