Skip to main content

AI Systems Master

Personal roadmap and reference library for becoming an AI Systems Engineer for regulated European industries by September 2027.

"I build production AI systems for European regulated industries on sovereign infrastructure. AI-Act-grade audit lineage. Sub-3s p95 latency. ~€0.04 per resolved query. Self-hosted models with signed containers. If you need an AI system a regulator can read, that's what I do."


What's here

SectionContent
PlaybookMaster career roadmap — 10 pillars, market demand, monetization path, interview readiness
Disciplines10 deep-reference files, one per skill domain
Projects3 flagship project specs — implementation blueprints, corpus targets, eval methodology, six benchmark numbers

The three flagship projects

ProjectDomainDifferentiator
Enterprise Knowledge PlatformAny / cloud10k+ docs, hybrid RAG, eval CI, observability
Workflow Automation PlatformBusiness workflowsAgents, MCP, human-in-the-loop, reliability engineering
Insurance Compliance CopilotRegulated / sovereignAI Act, PII pipeline, self-hosted models, audit lineage, Cosign

Project 3 runs on minicloud — the andrelair-platform sovereign Kubernetes stack.


The six benchmark numbers

Every flagship publishes these, with methodology:

  1. Groundedness rate (%)
  2. Citation accuracy (%)
  3. Refusal rate on out-of-scope (%)
  4. p50 / p95 / p99 latency (ms)
  5. Cost per resolved query (€)
  6. Hallucination rate on adversarial set (%)

Platform

Built on andrelair-platform — a 5-node bare-metal Kubernetes cluster (k3s + ArgoCD + Harbor + Vault + Authentik + Longhorn) simulating the IS of a French B2B insurer.

Platform docs: andrelair-platform.github.io/minicloud-platform-docs