AI architecture is not model design — it is systems engineering. This section documents production-grade machine learning architectures shaped by over 30 years of UNIX infrastructure experience, with a focus on reliability, observability, deterministic behaviour, and long-term operability in real production environments.
Incident Reconstruction: Beyond It Worked Yesterday
How bit-perfect replay, execution tracing, and sealed audit logs transform incident response from guesswork to forensics
Version Control for Deterministic Systems: Git Isn't Enough
How Merkle chains, cryptographic attestation, and reproducible builds satisfy certification evidence requirements
12 min read →Testing ML Systems: Beyond Unit Tests and Accuracy Metrics
A practical testing strategy for production machine learning
6 min read →Cost Engineering for ML Infrastructure
Where the money goes in ML infrastructure and what to optimise first
7 min read →State Management in ML Services: Beyond Stateless Inference
Architectural patterns for ML systems that need to remember
9 min read →Graceful Degradation in ML Systems
Fallback strategies for production inference that fails gracefully instead of failing loudly
9 min read →The Observability Blind Spot: What ML Metrics Miss
Why accuracy looks fine while your production system burns
11 min read →The Certifiable-* Ecosystem: One Deterministic ML Pipeline
Eight interlocking C99 projects that make every ML pipeline stage bit-identical and auditable
10 min read →Deterministic ML Pipeline for Safety-Critical Systems
How fixed-point arithmetic and cryptographic chaining produce bit-identical results from data to deployment
11 min read →WCET Analysis for Neural Network Inference
How to prove worst-case execution time for convolution, matrix multiply, and pooling operations
11 min read →10 of 17 articles