Skip to content
View PedroRuizCode's full-sized avatar
🛫
I'm flying
🛫
I'm flying

Organizations

@Kiwi-PUJ

Block or report PedroRuizCode

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
PedroRuizCode/README.md

Hey, I'm Pedro 👋

Electronic Engineer · AI Developer · Open-Source Builder from Colombia 🇨🇴

I build useful things with AI, software, electronics, and occasionally wings.

Website LinkedIn BITSOL Profile Views


whoami

AI Developer at the Javeriana Analytics Center
Co-founder & Developer at BITSOL SAS
Electronic Engineer who enjoys making software talk to hardware
Currently exploring local AI, document intelligence, computer vision and UAVs
Based in Bogotá, Colombia

I like projects that mix disciplines: a bit of machine learning, a bit of engineering, some open source, and just enough chaos to make things interesting.


What I'm building

An open-source platform for managing, processing, connecting, and exploring digital archives.

It supports flexible metadata, documents, images, audio, video, search, automated workflows, and extensible AI-powered plugins. At BITSOL, I contribute to its development, deployment, backend, and document-processing ecosystem.

A privacy-focused AI fitness coach created for the Hugging Face Build Small Hackathon.

It analyzes workout history using small language models, supports Spanish and English, works with CSV exports, accepts voice input, and was designed around local inference with tools such as llama.cpp, GGUF, and Ollama.

A modular fixed-wing UAV for aerial image capture and photogrammetry.

This project combines electronics, software, aerodynamics, 3D printing, structural design, and the ongoing challenge of convincing an aircraft to behave as expected.

A practical setup and compatibility fix for running NVIDIA's LocateAnything-3B vision-language model locally on NVIDIA 50-series GPUs.


Toolbox

Languages

Python C Java MATLAB SAS

AI, data and local models

Hugging Face Ollama llama.cpp Computer Vision Machine Learning

Tools and platforms

Docker Linux Git VS Code Modal Optuna


Recent missions


Things I care about

  • Open-source software that people can actually understand and extend
  • AI that can run locally and respect user privacy
  • Technology for archives, memory, research, and social impact
  • Computer vision, robotics, electronics, and aerial systems
  • Building first, overthinking later
  • Giving credit to the people whose work makes mine possible

Outside the terminal

When I am not debugging something that worked perfectly five minutes ago, I am probably:

  • riding motorcycles 🏍️
  • gaming 🎮
  • designing or printing another drone part 🛩️
  • testing a local model that barely fits in VRAM 🔥

Let's build something interesting

Website · LinkedIn · BITSOL · ArchiHUB

Made with curiosity, open source, and probably too many Docker containers.

Pinned Loading

  1. Archihub-App/archihub-backend Archihub-App/archihub-backend Public

    Python 5