AI Penetration Testing Specialist – LLM/GenAI Security

About the role

We are hiring an AI Penetration Tester to join the VMPT team at a well‑known Islamic Bank in Kuwait. The position blends traditional penetration testing, secure code review, and AI red‑team activities to protect LLM/GenAI, machine‑learning and AI‑enabled applications such as chatbots, RAG pipelines and AI agents.

Key responsibilities

• Plan and execute AI penetration tests for LLM/GenAI and ML solutions, including model endpoints, orchestration layers, RAG pipelines and plugins.
• Design test cases aligned with OWASP Top 10 for LLM Applications (prompt injection, insecure output handling, data disclosure, supply‑chain risks).
• Perform adversarial testing using MITRE ATLAS techniques and validate security of agentic workflows, permissions and authorization boundaries.
• Build Python‑based test harnesses, fuzzing prompts, jailbreak suites and regression tests; extend tools such as PyRIT and Microsoft Foundry AI Red‑Team Agent.
• Conduct secure code reviews of Python AI application layers (prompt templates, retrieval logic, output processing, secrets handling, authZ checks).
• Carry out traditional web/API/cloud penetration testing for AI‑enabled applications, triage findings and verify remediation.

Required profile

• Bachelor’s degree in Computer Science, Cybersecurity, Software Engineering or related field.
• 3–7 years of experience in penetration testing, application security or red‑team operations.
• Demonstrated experience testing LLM/GenAI systems (prompt injection, jailbreaks, data exfiltration, agent/tool abuse).
• Strong hands‑on Python for security automation and test‑harness development.
• Practical experience with Azure security concepts and Azure AI / Azure OpenAI / Foundry deployments.
• Relevant certification such as OSCP, GPEN, AZ‑500, CCSP or similar; OSWE, BSCP, AI‑102 are strongly preferred.

Required skills

• Python programming
• Git and CI/CD integration
• Burp Suite and common penetration‑testing toolchains (Kali, scanners, API tooling)
• Azure security controls (identity, key management, logging/monitoring)
• AI red‑team tooling (PyRIT, Microsoft Foundry scans)