Hi, I'm Leo!
I'm an ML Engineer at SAP Labs, where I work on AI agent infrastructure and developer tooling. My main project is A3 — a Kubernetes-native platform for orchestrating autonomous, sandboxed AI agent fleets.
Outside of work, I'm involved with AI safety research as a SPAR Spring 2026 Research Fellow, and I've co-authored work that placed 4th at the Apart Research AI Manipulation Hackathon.
This blog is where I share technical deep dives, experiments, and thoughts on AI, systems, and software engineering.
Check out my latest posts below or connect with me on social media!
Featured
-
A3: Kubernetes for autonomous AI agent fleets
One message, four agents, zero hardcoded workflows. How first-principles infrastructure produces emergent capabilities.
-
MCP explained from first principles, spelled out in code
Demystifying MCP by building servers and clients from scratch with raw JSON-RPC, then connecting them to LLMs via function calling.