Senior Manager – Offensive Security Engineering & AI Security

We have an urgent requirement for Senior Manager – Offensive Security Engineering & AI Security Validation with OSCP or OSCE certified is required for our banking clients in Abu Dhabi ,UAE Strong experience on on AI/LLM red teaming & blue teaming experience is MUST Strong experience in Advanced Offensive Security Engineering – deep exploit knowledge, not just pentesting/tools-- Must AppSec problem owned end-to-end--Must

Strong experience in Security Automation & Continuous Validation – CI/CD-based, always-on security testing pipelines-- Must Strong experience in AI/LLM Security & Red Teaming – prompt injection, model attacks, OWASP LLM + MITRE ATLAS exposure.-- -Must linking detection (SAST, pentests) with prevention and remediation. Strong experience in Threat Intel to Test Engineering – convert MITRE/OWASP intel into automated attack test cases within strict SLAs --- Must Mandatory certification - OSCP OR OSCE ( one is Must to have ) We are seeking a Senior Manager – Cyber Security Engineering to lead offensive security engineering, continuous adversarial validation, and AI/cloud security testing. The role focuses on transitioning from periodic penetration testing to continuous security validation across cloud, infrastructure, and AI/ML systems, aligned to 1LoD/2LoD governance models in a regulated environment. The incumbent will own automated security validation pipelines, threat intelligence operationalization, and security metrics reporting, ensuring production systems are continuously assessed against evolving adversarial techniques. Experience Required

• 8–10 years in Cyber Security / Offensive Security / Red Team / Security Engineering
• Strong background in:
• Offensive security and penetration testing
• Cloud security (preferably AWS)
• Blue-team validation / security assurance engineering
• Adversarial simulation and continuous security testing frameworks
• Experience in financial services / regulated banking environment preferred

Mandatory Certifications

• Candidates must hold at least one OSCP or OSCE (mandatory requirement) plus additional certifications:
• Core Mandatory
• Offensive Security Certified Professional (OSCP) OR
• Offensive Security Certified Expert (OSCE)
• Additional Required / Strongly Preferred
• GIAC GPEN or GIAC GXPN
• GIAC GMLE or equivalent AI-security / ML security credential
• CREST Certified Simulated Attack Tester (CCT) (desirable, especially for banking/financial sectors)
• Emerging / AI Security Exposure (Preferred)
• Exposure or enrollment in AI security/red-teaming programs (e.g., Anthropic or equivalent frontier model security evaluation programs)

Core Responsibilities

• Continuous Security Validation
• Design and operate continuous adversarial testing pipelines across:
• Cloud infrastructure (AWS-focused)
• Application security layers
• AI/ML models and LLM supply chain
• Implement automated security validation aligned with a 2LoD-approved threat coverage matrix
• Replace periodic penetration testing with always-on security validation systems
• Threat Intelligence Operationalization (7-Day SLA)
• Ingest and analyze threat intelligence from:
• MITRE ATLAS (AI attack techniques)
• OWASP LLM Top 10
• Convert new adversarial techniques into automated test cases within 7 days
• Maintain a structured and auditable threat-to-test traceability pipeline
• Vulnerability Aggregation & Governance
• Own centralized defect tracking using tools such as:
• DefectDojo or equivalent vulnerability management platforms
• Deduplicate, classify, and manage security findings end-to-end
• Enforce severity-based remediation SLAs and gating controls before production release
• Security Metrics & Reporting
• Build and maintain executive dashboards (e.g., Power BI) tracking:
• Open findings
• Mean Time to Remediate (MTTR)
• Pipeline gate pass rate
• Prompt injection / AI attack block rate
• Provide governance-ready reporting for 1LoD/2LoD stakeholders
• Offensive Security & AI Red Teaming
• Conduct and oversee:
• Automated penetration testing using tools such as Horizon3.ai or equivalent autonomous pentest platforms
• AI red-teaming using tools like Garak, PyRIT, and LLM-based attack frameworks
• Develop adversarial test cases aligned with:
• OWASP LLM Top 10
• MITRE ATLAS framework
• Validate resilience of AI systems against prompt injection, data leakage, and model manipulation attacks
• Governance & Operating Model Alignment
• Maintain clear separation of responsibilities between:
• 1LoD: Continuous control validation and security assurance
• 2LoD: Independent red teaming and unknown-scenario adversarial testing
• Ensure compliance with internal risk governance frameworks in regulated environments

Skills: validation,security,offensive