Skip to main content

Welcome to Lieber Engineering Dev Training 👋

This is the engineering counterpart of the Sales Training: where that site explains what we offer, this one explains how we build it. Each page turns a service from our catalogue into concrete architecture, tooling, implementation steps, and a definition of done — with links to the primary sources behind every recommendation.


What you will find here​

SectionWhat it coversLevel
How We BuildShared engineering standards: IaC, CI/CD, observability, evals, securityBasic
AI-Native EngineeringWorking with coding agents as a forward deployed engineer: context engineering, AGENTS.md, memory, execution plans, skills, MCP, hooks, and the agent-ready toolchainBasicLab
AI Service ImplementationGenAI PoC, RAG, agentic platforms, productification, fine-tuning, AI assessmentBasicAdvanced
Private & Platform AISovereign and on-premise LLM deployment, STACKIT, managed cloud AI platformsAdvanced
Cloud Service ImplementationAssessments, migration, STACKIT, OpenStack and hybrid cloud, cloud-native developmentBasicAdvanced
Local AI & InferenceRuntimes, quantization, inference engineering, open models, serving at scaleBasicAdvanced
GraphRAG & RAG for AgentsEntity extraction, knowledge graphs, and retrieval as the knowledge base for small local agentsAdvanced
Local RAG LabA fully local RAG pipeline you run on a laptopLab
Contracting WorkDelivering as a contracting developer: customer communication, contracts and boundaries, accountability for what you ship (with or without AI), PoC expectations, and upsell from the developer sideBasic
Learning PathsCourses and certifications per role, with direct linksBasic

How to use this site​

  1. Read How We Build first — every service playbook assumes those standards.
  2. Working with coding agents? Start with AI-Native Engineering and finish with its lab before your first client repository.
  3. Before a project starts, read the playbook for that service end to end and walk its Definition of done with the team. Read Contracting Work before your first customer kickoff.
  4. New to local AI? Follow the path Local AI Basics → Inference Engineering → Local RAG Lab → GraphRAG & Entities → RAG for Small Agents → Serving at Scale.
  5. Use the Sources section at the end of each page to go deeper; fast-moving facts carry an as of date.
Keep it current

Open-model releases and inference engines move monthly. When you find a newer version, a better technique, or a dead link, update the page and its sources in the same change. See CONTRIBUTING.md in the repository for the page template.


Built and maintained by Lieber Engineering. For questions, contact your tech lead.