Applied AI & IoT Engineer Dylan Capaldi
I build privacy-first AI systems that run entirely on hardware I own — no cloud, no telemetry, no rent. If it phones home, it doesn’t ship.
From the deck plate to the rack.
I’m a U.S. Navy veteran now studying Applied AI & IoT Engineering at FIU. The Navy taught me to trust systems I can inspect, hold, and keep running when the connection drops — and that conviction runs through everything I build.
So I build local-first: the model, the data, the metrics, and the alerts all live on hardware in my own rack. Agents that take real actions, observability you can audit, and inference that never leaves the building.
Hardware you can touch
If I can’t pull the drive and hold it, I don’t fully trust it. Everything runs on owned silicon.
Private by construction
No cloud round-trips, no telemetry, no third-party model keys. Privacy is the architecture, not a setting.
Observable & shippable
Dockerized, CI/CD’d, instrumented with Prometheus & Grafana. If it isn’t monitored, it isn’t done.
Jarvis // multi-zone LLM agent system
A Dockerized tool-use agent on Flask + Ollama with a complete agentic loop, hardened with structured-output enforcement, schema validation, iteration caps, and a tamper-evident decision log. Model routing picks the right brain per task; an eval harness guards schema compliance and latency.
Tort Agent // local LLM workflow assistant
Qwen3.6 35B via Ollama with a modular tool architecture spanning Canvas LMS, Apple Notes, Obsidian, and weather APIs: morning brief, handwritten-note OCR (PyMuPDF + ocrmac), atomic concept extraction, and weekly summaries — piped to an Obsidian vault with YAML frontmatter and [[wikilinks]].
Privacy-First Homelab // 5-node AI & IoT infrastructure
5 nodes on repurposed hardware, zero cloud dependency. Observability as code (AdGuard DNS sinkhole, Prometheus + Node Exporter, Grafana), a FastAPI inference wrapper over the Tailscale mesh, and a Frigate CV pipeline (RTSP → QuickSync → MQTT → Home Assistant) that drives automated agent decisions.
vault-sync // local-first cross-device sync
Obsidian vault sync across Mac, Windows, and an always-on UGREEN NAS hub — Syncthing with end-to-end encryption, no cloud subscriptions. A launchd job exports Apple Notes to PDF daily into the vault inbox, where Tort Agent picks them up to OCR.
Languages & Frameworks
- Python
- Bash
- SQL
- Flask
- FastAPI
- Uvicorn
Infrastructure & DevOps
- Docker / Compose
- GitHub Actions
- Tailscale
- Linux (Ubuntu Server)
- systemd
- Prometheus
- Grafana
AI / LLMs
- Ollama
- Tool-use loops
- Model routing
- Structured outputs
- Eval harnesses
- RAG concepts
IoT & Security
- Home Assistant
- Frigate NVR
- Zigbee2MQTT / MQTT
- AdGuard Home
- SIEM / IDS
- Zero-trust networking
Google Cybersecurity Professional Certificate
SIEM, intrusion detection, network security, and Python security automation — the security mindset behind every system I run.
Let’s build something
that runs on its own.
Open to roles and collaborations in applied AI, IoT, and local-first infrastructure. Best way to reach me is GitHub or LinkedIn.