g
greyursus

Jose Reyes

@greyursus

Local AI Automation Specialist

Verenigde Staten
Engels, Spaans
Sommige informatie wordt in het Engels weergegeven.
Over mij
My name is Jose Reyes. Before AI, I worked in security and sales — two fields that taught me a lot about paying attention to what people actually need, not just what they say they want. I got into automation because I like to tinker, and because I believe personal security matters more than most companies treat it like it does. The deeper I got into the AI space, the more I wanted to build something different: automation where your data isn't being used to train someone else's product, and where you're not stuck with a dumbed-down tool because you didn't pay for the "enterprise" tier.... Lees meer

Skills

g
greyursus
Jose Reyes
offline • 

Bekijk mijn diensten

Berichten sturen en e-mailen
I will set up a private local ai chatbot for your documents
VanafUS$ 75 / projectMeer informatie
Implementatie en uitrol van AI
I will make n8n automation with approval gates
VanafUS$ 100 / projectMeer informatie

Portfolio

Werkervaring

Self_Employed

Private/Local AI Automation Specialist | Ollama, RAG, n8n Workflows

Self Employed • ZZP

Jan 2026 - Present • 7 mos

I build private, self-hosted AI automation for businesses that don't want their data training someone else's model. Everything I deliver runs on infrastructure you control — no per-seat SaaS fees, no vendor lock-in, no silent data collection. What I've built and can build for you: • Local LLM deployment (Ollama) — document Q&A, inbox triage, and intake automation running entirely on private hardware, zero cloud API calls • RAG systems with pgvector — search and Q&A across your own document sets, with retrieval tuned to your actual content, not a generic chatbot wrapper • Multi-step automation workflows (n8n) — including human-approval checkpoints built directly into the pipeline, so nothing executes without your sign-off • Tiered model routing — cheap, fast models handle routine requests; only complex cases escalate to a stronger (and more expensive) model, keeping your ongoing costs predictable I run a self-built homelab (Proxmox virtualization, dual-GPU AI workstation, production PostgreSQL/pgvector) as my actual working environment — every service I offer, I run myself first before I sell it. Let's talk about what's eating your team's time on repetitive tasks, and whether a private automation setup makes sense for your scale.