Course Objective & Scope
Security cannot scale when individual business units connect directly to external LLM APIs, Shadow AI proliferates and controls vary from project to project. This course presents a holistic secure enterprise reference architecture combining a central AI gateway, private networking (Private Link / VPC Endpoints), identity and access management, permission-aware RAG infrastructure and isolated agent execution environments.
Participants compare Azure AI Foundry, Amazon Bedrock, Vertex AI and on-premises (vLLM) deployment models and produce a layered AI reference architecture and security control plan tailored to their organisation.
Who Should Attend?
- Enterprise architects, cloud architects and security architects
- Engineering teams building AI platforms and LLMOps infrastructure
- CISO office, information security and technology leaders
- Prerequisite: knowledge of cloud architecture, network security and enterprise integration patterns
Key Takeaways
- Design a multi-layered enterprise AI reference architecture aligned with Zero Trust principles
- Position a central AI gateway and policy enforcement layer governing all model traffic
- Evaluate cloud, hybrid and on-premises model hosting options from a security perspective
- Establish network and data isolation for RAG, vector databases, memory and MCP servers
- Define centralized audit logging, quota/cost governance and incident response integrated with SIEM/SOC
Curriculum
Principles of Enterprise AI Security Architecture
- Shadow AI risks and moving from project-by-project patchwork to platform security
- Applying Zero Trust across application, orchestration, AI gateway, data/RAG and model layers
Central AI Gateway and Traffic Governance
- Authentication, central key management (Vault/KMS), rate limiting and budget quotas
- Gateway-level PII masking, guardrails, model routing and DLP integration
Cloud, Hybrid and On-Premises Model Hosting Security
- Private Link, customer-managed keys (CMK) and zero-data-retention in Azure AI Foundry, Bedrock and Vertex AI
- On-premises vLLM/TGI clusters, GPU isolation and confidential computing for regulated workloads
Secure Data, RAG and Agent Infrastructure
- Permission-aware enterprise search, vector database encryption and tenant isolation
- Agent execution zones, MCP gateways, egress filtering and sandboxing layers
Observability, Auditing and Compliance Architecture
- OpenTelemetry tracing, privacy-preserving logging and SIEM/SOC integration
- Mapping KVKK, sector regulations, ISO/IEC 42001 and EU AI Act controls into architecture
Other Courses in This Category
-
Comprehensive training on PII masking, reversible pseudonymisation, anonymisation and data residency architectures to adopt LLMs without exposing personal or confidential corporate data.
- Live Course
- 5 modules
-
Hands-on training on building a low-latency PII detection, masking and de-pseudonymisation gateway in front of LLM APIs using Microsoft Presidio, GLiNER and Turkish rule/NER recognisers.
- Live Course
- 5 modules
-
Teaches how to replace production customer data in testing, analytics and LLM evaluation environments using k-anonymity, differential privacy and SDV/LLM-based synthetic data generation.
- Live Course
- 5 modules
-
Teaches how to scrub personal data from LLM and agent telemetry in OpenTelemetry, Langfuse and SIEM logs, and engineer retention policies, access controls and KVKK compliance into observability pipelines.
- Live Course
- 5 modules
-
Covers Agent Goal Hijack—the top OWASP Agentic AI risk—showing how attackers divert autonomous planning loops, persistent memory and multi-step execution, and how to defend against it with intent verification.
- Live Course
- 5 modules
-
Covers tool poisoning, rug pulls, tool shadowing and supply chain risks in Model Context Protocol (MCP) servers, third-party agent tools and A2A integrations, and how to build a secure MCP architecture.
- Live Course
- 5 modules
Get in touch
