Applied AI Engineering · Key Largo, FL

Practical guides for production AI systems

Measured benchmarks, clear architecture trade-offs, and code that runs.

I'm Steven W. White, a software engineer and AI builder with 25+ years shipping distributed systems, computer vision, and applied ML. When a new model architecture, retrieval pattern, or serving optimization lands, I run it on GPUs, measure what holds up, and publish the full implementation from the Florida coast.

27

Runnable Tutorials

5

Engineering Tracks

25+ yrs

Systems & ML Craft

Interactive Engineering Lab · 3 Simulators GPU VRAM & KV-Cache · Hybrid Retrieval & Reranking · Agent Memory

AI Systems Engineering Lab: Serving, Retrieval & Memory

Size GPU VRAM and KV-cache topologies from 2K to 128K context, model two-stage BM25 + dense RRF and cross-encoder reranking latency SLOs, and compare quadratic multi-turn agent transcripts against consolidated slot memory.