Building autonomous AI that works while I sleep. Six agents, seven models, zero cloud bills — self-hosted on bare metal in Toronto.
A self-hosted multi-agent AI system running 24/7 on a Lenovo M720Q in Toronto.
Every retrieval pipeline in Groot ships with eval scores. Here are the real numbers.
// BUILD LOG
From a blank Ubuntu install to a fully autonomous 6-agent AI system. Every milestone is real.
Selected Lenovo M720Q (i5-8500T, 16GB). Researched LangGraph, Ollama, ChromaDB. Decided on local-first, zero cloud AI dependency.
Ubuntu 22.04.5 LTS bare metal. LUKS full-disk encryption. WiFi driver (RTL8852BU). Tailscale VPN. First Ollama model running.
FastAPI agent service. Groot supervisor routing to qwen2.5:7b. ChromaDB setup with 6 collections. Basic RAG pipeline working end-to-end.
Custom asyncio priority queue with RAM headroom validation. Hybrid RAG: BM25(40%) plus Dense(60%). Real retrieval quality improvement measured.
Adzuna Canada API. ATS-optimized resume tailoring. PDF generation via reportlab. Telegram delivery in under 60 seconds.
guardrails-ai: PII detection, prompt injection blocking, toxic content filter. Ragas evaluation: Faithfulness 1.000. 20-test red-teaming framework.
6 agents live. 7 models, 27GB. n8n workflows. Notion nightly diary. React dashboard with 12 pages. Supervisor loop runs hourly. 4,190+ hours and counting.
Production-minded projects — tested, evaluated, and mostly still running.
Self-hosted 6-agent AI system with hybrid RAG, guardrails, and Ragas evals — orchestrated by LangGraph, served by Ollama, reachable over Slack and Telegram. Running 24/7 on bare metal.
Stateful data-analysis assistant with conversation memory. 74 tests, full CI pipeline.
Structured-output resume screening with schema-validated LLM responses behind a FastAPI service.
Adversarial test harness for LLM pipelines — 20 attack tests plus Ragas scoring at 1.000 faithfulness.
Natural-language querying over relational data, powered by qwen2.5-coder:7b with schema-aware prompting.
Pydantic-validated extraction pipeline that turns messy documents into clean Notion databases.
Building AWS ETL pipelines across S3, Glue, Lambda, and Redshift. Optimizing SQL workloads, monitoring pipeline health, and shipping in Agile sprints.
Designed and operate a 6-agent AI system with hybrid RAG and thermal-aware load scheduling. Enforcing output quality with guardrails-ai, measuring it with Ragas, and automating everything else with n8n.
Built an explainable credit-risk model with SHAP and Scikit-learn, improving accuracy by 40% through feature engineering and WoE binning.
Open to Data Engineer · ML Engineer · LLMOps Engineer roles