Ir al contenido
JM

Juan Manuel

|

Elche, Alicante, Spain

Physicist and AI engineer specialized in computer vision. Solving complex problems with high-impact AI.

Juan Manuel Ruiz Muñoz

About me

Physicist and mathematician specialized in Machine Learning and Computer Vision engineering. I build computer vision systems that work in real production: from data capture and preprocessing to model deployment. I am drawn to the intersection between mathematical rigor and AI solutions with tangible impact. When I am not training models, I write about physics, chaos and meteorology on this blog.

...

Experience

0

Projects

AI

Specialist

Download CV

Projects

In production

Tire Defect Detection

Computer vision pipeline for automatic defect detection in the tire industry using deep learning.

PyTorch OpenCV Docker AWS
Published

AI Misinformation Detection

Ontology-based AI architecture for detecting misinformation in fiction works. Published at DCAI'25.

NLP Transformers Python Ontologies
Completed

Lagrangian Atmospheric Blocking

Lagrangian method for automatic identification of atmospheric blocking situations using HYSPLIT trajectories.

Python HYSPLIT ERA5 MATLAB
Active

Talk to Me

CLI for practicing conversational English with an AI tutor. Speak through your microphone, Whisper transcribes your voice in real time, and a local LLM (Ollama) keeps the conversation going.

Python Whisper Ollama CLI
Active

Local Agent with Ollama

Conversational console agent running 100% locally on Ollama. Native tool calling: file read/write, web search with DuckDuckGo, Python code execution, and RAG with ChromaDB to query your own documents.

Python Ollama ChromaDB RAG
In development

Frontend: An Introductory Course

Educational frontend web development repository. Covers HTML, CSS and modern layouts (Flexbox/Grid) with detailed theory and commented examples. Under progressive development.

HTML CSS Flexbox Grid
Active

Personal Portfolio

This website: a static portfolio built with Hugo and Tailwind CSS, deployed on GitHub Pages with CI/CD.

Hugo Tailwind CSS JavaScript GitHub Pages

Experience

ML Engineer · Computer Vision & LLMs

VRAIA Corp.

June 2025 - Present

I take defect detection and segmentation models (CNNs, ViT, YOLO, RF-DETR) and a multimodal OCR (GLM-OCR) to production for industrial tire inspection: mAP@50:95 of 0.83 and 98.56% exact match reading sidewalls.

I write about this work in OCR in extreme conditions and CNNs vs Vision Transformers.

PyTorch Vision Transformers YOLO RF-DETR GLM-OCR LoRA vLLM Docker

Data Scientist & AI Researcher

AIR Institute & BISITE Research Group

June 2024 - June 2025

Research in NLP and LLMs: an ontology-based misinformation-detection architecture built with LLM-generated ontologies (published at DCAI'25), RAG pipelines and multi-agent systems, plus computer vision projects.

Publication: DCAI'25 paper.

NLP LLMs RAG ChromaDB Multi-agent Ollama Computer Vision Python
January 2024 - July 2024

I developed Lagrangian methods to automatically identify atmospheric blocking situations — the basis of my thesis and a publication in progress.

I tell the full story in Atmospheric blocking, a Lagrangian view.

Python Atmospheric Physics HYSPLIT ERA5 DBSCAN

Latest Blog Post

Education

Bachelor's Degree in Physics

Universidad de Alicante

+120 ECTS from the Mathematics degree taken in parallel (UA simultaneous-studies program).

2020 - 2024

Thesis: A Lagrangian method for the identification of atmospheric blocking situations

View Thesis

SICUE Exchange — Physics & Mathematics

Universidad de Salamanca

International mobility scholarship.

2022 - 2023

Publications

In development

A Lagrangian Method for the Identification of Atmospheric Blocking Situations.

DCAI'25

AI-Powered Ontology-Based Architecture for Misinformation Detection in Fiction Works.

Download Paper
Juan Manuel Ruiz Muñoz

Juan Manuel

Computer Vision