AI Engineering
Building a Resilient RAG Pipeline
Why most RAG demos break in production, and the retrieval, evaluation, and guardrail patterns that make retrieval-augmented generation dependable at scale.
1 min read
AI · Cloud · Systems
Building production-grade distributed systems that hold up under real load.
I'm Lanford Yenn, a cloud solution architect. I write about cloud-native architecture, AI engineering, and the trade-offs that only surface in production.
01
AI Engineering
Production AI systems — RAG pipelines, evaluation harnesses, and the operational discipline required to ship LLM features that actually hold up in production.
02
Cloud Architecture
Cloud-native foundations on AWS and Kubernetes: resilient service design, infra-as-code, and platform abstractions that let teams move quickly and safely.
03
System Design
Distributed systems done carefully — event-driven backends, data consistency, and the trade-offs that only become visible under real load.
Latest writing
All posts →Featured work
All projects →2026★ Featured
AI Knowledge Assistant
A production retrieval-augmented assistant for an internal documentation corpus, with eval harness and grounded-answer guardrails.
Cut average support resolution time by 38% with a grounded, evaluated RAG assistant.
TypeScriptPythonLangChainPostgreSQL + pgvector
2025★ Featured
Internal Developer Platform
A golden-path Kubernetes platform with custom controllers that let teams ship services without writing boilerplate manifests.
Reduced mean service onboarding time from days to under 30 minutes.
GoKubernetesTerraformArgoCD