Pleased to share that I have officially earned the AWS Certified Generative AI Developer – Professional credential.

Transitioning Generative AI from isolated prototypes into reliable, enterprise-grade production systems requires far more than prompt engineering. Preparing for this certification reinforced key architectural trade-offs across the full GenAI lifecycle:

  • Production RAG & Data Engineering: Designing scalable vector retrieval pipelines, chunking strategies, and grounded knowledge systems that balance latency, cost, and retrieval accuracy.
  • Agentic Workflows & Tool Orchestration: Building deterministic, multi-step agent architectures with structured tool execution, persistent memory management, and verifiable output trajectories.
  • Enterprise Security & Governance: Implementing Zero Trust network perimeters, IAM-based access controls, PII redaction, and guardrails to protect sensitive enterprise workloads.
  • Operational Excellence & Cost Optimization: Evaluating model selection trade-offs, throughput provisioning, automated LLM-as-a-judge evaluations, and observability across production deployments.

Many of these exact architectural patterns directly mirror what I have been building and documenting in my ongoing hands-on series on Amazon Bedrock AgentCore and the Strands SDK—and I will be publishing Part 5 of the series next week.

For anyone else preparing for this exam or architecting production GenAI workloads on AWS, I am always glad to connect.

About the Author
Jonathan Wong is an IT and AI consultant with 20+ years of experience leading engineering teams across Vancouver and Hong Kong. He specializes in modernizing legacy platforms, cloud security, and building AI-ready systems for startups and large enterprises while advising leadership on using strategic technology to drive business growth. 
Connect with me on LinkedIn

Categorized in:

AI, AWS, Certification, Cybersecurity,

Tagged in:

, , , ,