AI Offensive Testing Specialist

Within the CISO Offensive Security Tribe, the AI Offensive Testing Specialist executes and improves Euroclear’s LLM-supported security-testing activities. As a member of the delivery team, the role performs AI-assisted SAST, DAST, penetration-testing and red-team activities within approved scope, methodology and human-oversight controls.

Working with the AI Offensive Testing Technical Lead, Offensive Security specialists, application teams and platform engineers, the Specialist prepares testing inputs, operates the technical environment, validates outputs and produces reproducible, evidence-rich findings.

Key Accountabilities

1. Test Preparation & Secure Execution

Prepare approved test scope, application context, source code, endpoints, credentials, test data and prerequisites for LLM-supported assessments.
Execute SAST, DAST, penetration-testing and red-team workflows within authorised rules of engagement, access controls and safety constraints.
Handle sensitive source code, credentials, testing artefacts and assessment evidence in accordance with defined security and data-handling requirements.
Monitor execution, troubleshoot operational issues and escalate technical, safety or scope concerns to the Technical Lead.

2. LLM-Supported Testing & Method Improvement

Configure and operate approved models, agents, prompts and tools to support reconnaissance, analysis, test generation, hypothesis development and evidence capture.
Apply standard test scenarios and compare outputs across approved models or configurations using defined quality, repeatability, duration and resource measures.
Capture complete evidence covering target, code or asset location, weakness hypothesis, technical proof, affected paths, remediation proposal and validation status.
Propose improvements to prompts, configurations, test cases, datasets and workflows based on practical assessment results.

3. Finding Validation & Remediation Support

Validate findings for accuracy, code or asset reachability, exploitability, attack paths, affected-component deployment and control effectiveness.
Distinguish actionable vulnerabilities from false positives, duplicates, non-reachable code and unsupported hypotheses, escalating complex cases for review.
Maintain human validation and obtain explicit approval before intrusive testing or before findings enter risk, remediation and reporting workflows.
Explain findings and remediation options to developers, application owners and security teams, and perform retesting to validate corrective actions.

4. Assessment Delivery & Lifecycle Integration

Deliver assigned LLM-supported scans and tests on time, ensuring outputs are complete, reproducible, technically credible and reviewable.
Collaborate with internal specialists and external providers on SAST, DAST, penetration-testing and red-team use cases, prerequisites and rules of engagement.
Record validated findings in the required risk, remediation and reporting workflows and maintain supporting evidence through closure.
Identify recurring deterministic findings that could become secure patterns, automated tests, SAST rules, detection content or CI/CD quality gates.

5. Operationalisation & Team Contribution

Follow and help improve runbooks, operating procedures, service controls, authorised scope, approval steps, rollback and testing safeguards.
Support environment testing, deployment validation, integration testing, onboarding, monitoring and operational-readiness activities.
Document lessons learned, reusable test patterns and technical procedures, and contribute to knowledge sharing and continuous service improvement.

Your Profile

Qualifications & Experience

At least 3 years in application security, penetration testing, offensive security, security engineering or software engineering within enterprise environments.
Hands-on knowledge of source-code analysis, SAST, DAST, web and API security testing, penetration testing or red-team techniques.
Practical experience using LLMs or AI agents for coding, security analysis, automation or structured technical evaluation.
Ability to assess code and asset reachability, exploitability, attack paths, control effectiveness and remediation options.
Experience working with secure cloud or containerised environments and handling sensitive source code, credentials and security-assessment data.
Coding or scripting capability and disciplined use of version control, testing, logging and technical documentation.
Experience contributing to the operationalisation of an AI, automation or security capability is preferred.

Skills & Competencies

Application security, offensive security, SAST, DAST, pene