I build AI agents and production infrastructure for industrial companies. 10+ years bridging the physical world — sensors, machines, factory floors — with intelligent automation that runs unsupervised.
I take on consulting projects when the problem is interesting. If you're figuring out how AI agents, predictive maintenance, or infrastructure automation could work for your business, let's talk.
AI Agent Systems — Multi-agent platforms with MCP servers, cognitive memory, safety boundaries, and real-time infrastructure monitoring. Production systems, not demos.
Infrastructure — Kubernetes on bare metal, GitOps with ArgoCD, CI/CD pipelines, GPU passthrough for LLM inference, automated everything.
IIoT & Predictive Maintenance — Vibration analysis, sensor architectures, condition monitoring pipelines, and the analytics that keep machines running.
Python TypeScript Go Kubernetes ArgoCD OpenTofu Proxmox Prometheus Grafana PostgreSQL Qdrant FastMCP
- Building Karpathy's LLM Wiki: A Production Homelab Implementation (2026-04-13)
- Proxmox API Tokens: Bash History Expansion and the ! Character (2026-04-11)
- AMD iGPU Stealing Your RAM: UMA Frame Buffer on Headless Servers (2026-04-10)
- Agent Credential Management: Two-Tier Service Accounts for Secure AI Agent Workflows (2026-04-10)
- Infrastructure as Code, but Automated: OpenTofu and GitHub Actions (2026-04-08)
The best technology work happens at the boundary between domains.