Essential qualifications and experience

•       Bachelor’s degree in any discipline, or equivalent professional experience; demonstrated engineering practice is the primary criterion.

•       Minimum 6 years in security engineering, application security, offensive security, detection engineering or cloud security.

•       Minimum 1–2 years of hands-on work securing or testing production generative AI, LLM or agentic systems.

•       Demonstrated experience red-teaming AI systems against prompt injection, jailbreaks, excessive agency and model abuse — candidates should be able to walk through specific findings they produced.

•       Strong Python, with the ability to build test harnesses, automation and tooling to a production standard.

•       Solid cloud security engineering experience on a major hyperscaler; Azure preferred.

•       Practical understanding of LLM application architecture: embeddings, vector databases, RAG, agent frameworks, tool and function calling, and the MCP-style integration pattern.

•       Working knowledge of OWASP Top 10 for LLM Applications, OWASP agentic security guidance and MITRE ATLAS.

•       CI/CD and infrastructure-as-code fluency; comfortable embedding security checks into delivery pipelines.

•       Practical use of current AI development tooling — agent-building platforms, AI-assisted coding environments and locally hosted models — to build tooling and evaluation harnesses at speed.

•       Clear written reporting — findings must be reproducible and actionable by the receiving team.