I design and build complete systems — from endpoint and networking to enterprise infrastructure, and now autonomous AI architectures. 18+ years of experience spanning IBM/AstraZeneca-scale consulting, full IT ownership as a CTO, and hands-on systems administration across the legal, healthcare and research sectors.
📍 Sweden · 🌐 Open to remote · 💬 Swedish / English
- Architecture & Infrastructure — end-to-end systems · networking · Active Directory / M365 · Linux / Apache · performance & hardware tuning
- Applied AI — local LLMs · multi-model orchestration · persistent-memory architectures
- Engineering — PowerShell · Python · C/C++ · automation · Windows internals
Kollektivet — Det digitala kollektiva medvetandet ("the digital collective consciousness")
A self-built distributed AI architecture: one persistent, shared "mind" that any model or tool can plug into — from a CLI agent to a local llama-server model — so models build on each other's reasoning and the system compounds over time. Built solo: C++ integration into llama.cpp, graph-based memory (Neo4j/Aura), self-directed model tiering, and closed-loop debugging.
- Public fix accepted to Microsoft's
intelligent-terminal(#328) - Published Chrome extension (TOTP / MFA)
- Contributor to llama.cpp-based tooling
- 📄 CV / Resume: autom8edIT.github.io
- 💼 LinkedIn: linkedin.com/in/joel-larsson
- 📧 Email: joel.larsson@autom8ed.me


