Manager AI Security Assurance
Johannesburg - South Africa
Job Summary
The key objective of this role is to provide independent security assurance across the end-to-end Artificial Intelligence (AI) and Large Language Model (LLM) estate. The role tests validates and assures the security of AI solutions from the models themselves through to the surrounding architectural components such as AI firewalls API gateways retrieval (RAG) pipelines and inference endpoints.
This is a testing- and assurance-focused role. The incumbent is responsible for adversarially testing (red-teaming) AI/LLM systems validating that security controls operate as designed and providing evidence-based assurance to architecture and governance forums that AI solutions are safe to deploy and operate. The role provides independent technical security verification rather than building the controls themselves.
- Bachelors or Masters degree in Computer Science Information Security or related field.
- Relevant certification/accreditation/membership with professional body as required
- Offensive security / penetration testing certifications (e.g. OSCP OSEP GPEN CRTO).
- AI/ML security certifications and recognised AI red-teaming / adversarial ML training.
- CISSP CEH or equivalent security certification.
- Cloud security certifications (Azure AWS or GCP Security).
- Minimum 810 years in cybersecurity with at least 5 years focused on security testing penetration testing or red-teaming.
- Demonstrable experience testing AI/ML or LLM systems (adversarial ML prompt injection jailbreak and data-leakage testing).
- Experience testing API security and API gateways (e.g. Apigee Kong AWS API Gateway Azure API Management).
- Hands-on experience with AI firewalls / LLM gateways and content-filtering / guardrail technologies.
- Familiarity with securing data pipelines: encryption at rest and in transit tokenization and data masking.
- Working knowledge of AI security frameworks: OWASP LLM Top 10 MITRE ATLAS NIST AI RMF and ISO/IEC 42001.
Functional Knowledge:
- Deep understanding of AI/LLM attack techniques and threat models (prompt injection data poisoning model extraction membership inference evasion).
- Strong knowledge of AI architecture components: models inference endpoints RAG / vector stores AI firewalls API gateways and orchestration / agent frameworks.
- API security testing (authentication authorisation OWASP API Security Top 10).
- Adversarial machine learning and model robustness / safety testing.
- Understanding of guardrail and content-moderation technologies and how to verify their effectiveness.
- Compliance with PSD2 GDPR PCI DSS POPIA and emerging AI regulation (e.g. EU AI Act).
- Understanding of the Agile and DevSecOps delivery processes (SCRUM Kanban preferable)
Required Experience:
Manager
About Company
With 15 years of experience in the Telecommunications and Financial Services industry in Africa and the Middle East, we are experts at supporting our clients through their digital transformation journeys. We believe in blending traditional methods with cutting-edge strategies to drive ... View more