Hi, my name is

Pol Casacuberta

I turn data into intelligent solutions.

Computer Science Engineer specializing in AI, data science, and machine learning. Currently working as an AI & Data Consultant, turning complex data into actionable insights and intelligent solutions.

View my work
About

A bit about me

Hello! I'm Pol — a Computer Science Engineer from Barcelona with a passion for AI, data science, and machine learning. I graduated from UPC's Facultat d'Informàtica de Barcelona (FIB) and have been working at the intersection of data and intelligent systems ever since.

I believe in standing on the shoulders of giants — leveraging the best of existing knowledge and technology to build innovative solutions. From predictive analytics and data governance to computer vision and neural networks, I enjoy tackling complex problems that drive real impact.

Here are some technologies I've been working with recently:

  • Python
  • SQL & Power BI
  • AWS & Azure
  • Machine Learning
  • Informatica
  • Computer Vision
Download CV
Pol Casacuberta
Interactive

Try my projects

Live, interactive demos you can play with right in your browser.

Live Demo

Bachelor's Thesis — Polyp Detection

Deep learning polyp detection with generative data augmentation (CycleGAN/SPADE). Explore model results and the training pipeline.

  • PyTorch
  • CycleGAN
  • Object Detection
  • UPC
Live Demo

Draculin

Health tracking app with AI chatbot and computer vision, built with Flutter. Finalist at BitsXLaMarató 2023.

  • Flutter
  • Django
  • AI
Live Demo

BitsXLaMarató — Aorta

Winner of BitsXLaMarató 2022 — Ultrasound → Mask R-CNN aorta segmentation and 3D reconstruction; browser mock inference + diameter explorer.

  • PyTorch
  • OpenCV
  • 3D
  • CV
Live Demo

License Plate Detection

Detect and read license plates from car images using computer vision — a MATLAB pipeline ported to the browser.

  • Computer Vision
  • TypeScript
Live Demo

Programming Game Viewer

Watch AI bots battle on a grid — warriors, builders, weapons, and strategy. Full-stack game viewer with live C++ engine, Canvas rendering, and interactive replay controls.

  • Mithril.js
  • Canvas
  • C++
  • FastAPI
Live Demo

JSBach Interpreter

Write and play music with a custom programming language. A browser-based interpreter for the JSBach musical language.

  • ANTLR4
  • Web Audio
  • Language
Live Demo

Tenda Online

A full e-commerce store with product browsing, shopping cart, and checkout flow.

  • PHP
  • MySQL
  • E-Commerce
Live Demo

WPGMA Clustering

Build phylogenetic trees step by step. Input species with gene sequences and watch the WPGMA algorithm merge clusters into a dendrogram.

  • TypeScript
  • Algorithms
  • D3
Live Demo

MPIDS Solver

Interactive graph dominance solver with D3 force-directed visualization. Find the minimum positive influence dominating set using greedy and SA-style local search.

  • Elm
  • D3.js
  • FastAPI
  • Graph Theory
Live Demo

Graph Phase Transitions

Explore connectivity and complexity phase transitions on binomial, geometric, and grid random graphs with real-time percolation animation and Monte Carlo sweep charts.

  • Lit
  • Canvas
  • FastAPI
  • NetworkX
Live Demo

Travel agency (PDDL)

Automated planning practice: PDDL domain for trips with flights, hotels, numeric constraints, and metric minimization.

  • PDDL
  • Planning
  • UPC
Live Demo

Desastres IA

Disaster relief as local search: helicopters rescue groups from centers using hill climbing and simulated annealing. Full-stack web solver with interactive 2D map and experiment dashboard.

  • Solid.js
  • FastAPI
  • Local search
  • Canvas
  • UPC
Live Demo

Machine Learning — Hypothyroid

Hypothyroid classification task: Nbviewer, GitHub links, k-NN click demo tied to binaryClass N/P (FIB-UPC).

  • Python
  • Jupyter
  • sklearn
  • UPC
Live Demo

Recommendation System

A web interface for a content-based recommendation system built with Java, Spring Boot, and Thymeleaf.

  • Java
  • Spring Boot
  • Recommendation
Live Demo

CAIM IR Explorer

Interactive information retrieval explorer running in-browser: compute PageRank on the global airport network with a D3 world map, and analyze Zipf's Law on text corpora with curve fitting.

  • Vanilla TS
  • D3.js
  • FastAPI
  • PageRank
Live Demo

Trip Planner (Expert System)

An expert system trip planner: answer 10 questions about your travel preferences and get a full itinerary with cities, hotels, activities, transport, and cost. Reimplements CLIPS rules in Python.

  • HTMX
  • Alpine.js
  • Litestar
  • Expert System
Live Demo

Parallel Computing Labs

Five OpenMP labs compiled to WebAssembly: Mandelbrot set, heat equation solver, 4-way merge-sort, pi computation, and parallel speedup benchmarks — all running in your browser.

  • C
  • OpenMP
  • WebAssembly
  • Preact
  • Canvas
Live Demo

Robotics Dashboard

Interactive robotics visualizations: mobile robot odometry replay, wall-following simulator, 3D robot arm FK (Puma560/3-Link), trajectory planner, sensor dashboard, and EKF state estimation — all with real lab data.

  • Ember.js
  • Babylon.js
  • Robotics
  • Canvas
  • EKF
Live Demo

Algorithm Visualizer

Interactive step-by-step visualizations of 18 algorithms: Dijkstra, Prim, DFS, topological sort, BFS maze, flood fill, Sudoku, merge/insertion/radix sort, N-Queens, binary search, GCD, matrix exponentiation, and 2-opt TSP.

  • Qwik
  • Canvas
  • Algorithms
  • Graphs
  • Sorting
Live Demo

Computer Graphics Shader Playground

Interactive WebGL2 shader playground porting FIB-UPC Computer Graphics labs: vertex transforms, Phong lighting, procedural textures, fragment patterns, geometry shader emulation, and advanced effects — all running live GLSL in your browser.

  • WebGL2
  • GLSL
  • Shaders
  • UPC
Skills

Tech I work with

Technologies and tools I use to bring ideas to life.

Programming Languages

Python]TypeScript]JavaScript]C]C++]Java]SQL]

AI & Data Science

Machine Learning]Computer Vision]PyTorch]scikit-learn]OpenCV]LangChain]Object Detection]Generative Models]MLOps]Data Mining]Statistics]

Tools & Platforms

AWS]Azure]GCP]Docker]GitHub Actions]PostgreSQL]FastAPI]Git]Jupyter]

CS Fundamentals

Algorithms]Software Architecture]Parallel Processing]CI/CD]Compiler Design]Cybersecurity]
Experience

Where I've worked

A timeline of my professional journey so far.

  • Sep 2025 — Present

    AI & Data Consultant @ Deloitte

    • Led a multidisciplinary team to design and deliver AI and data-driven use cases for public sector initiatives
    • Worked on the Generalitat de Catalunya project, focusing on Data Governance, client relationship management, and consulting strategy
    • Hands-on experience with Informatica, AWS, and Azure in real-world data management solutions
  • Sep 2023 — Sep 2024

    Data Engineer @ MGS, Seguros y Reaseguros S.A.

    • Championed predictive analytics, robust data governance, and optimized ETL processes, enhancing data quality and efficiency
    • Drove a 20% increase in report accuracy with impactful visualizations using Python, R, SQL Server, and Power BI
    • Crafted dynamic dashboards for real-time KPI and business metric monitoring, enabling informed strategic decisions
  • Jan 2022

    Software Development Engineer @ bitsxlaMarató TV3 Hackathon (Winner)

    • Developed an aneurysm detector using a convolutional neural network with MaskRCNN for cardiovascular health
    • Won the bitsxlaMarató TV3 Hackathon 2022 for this project
    • Designed a user-friendly interface for uploading video, detecting the aorta, and visualizing 3D models
Professional Work

Featured Projects

Key milestones and AI initiatives delivered in the real world.

Horse

Physical AI Anomalies Detection

AI & Data Consultant @ Deloitte

The world's first Physical AI project delivered at Deloitte. Detected manufacturing anomalies on live motor production lines in real-time. Also developed a digital twin of the warehouse with camera tracking for packages.

  • Physical AI
  • Computer Vision
  • Digital Twin
  • IoT
  • Real-time
Gobierno de Aragón

E2E AI Talent Matching Platform

AI & Data Consultant @ Deloitte

End-to-end software that parses PDF resumes, standardizes them into structured JSON, and indexes them in a RAG database. Allows semantic querying to find the best candidates for a job description and vice versa.

  • LLMs
  • RAG
  • Vector Search
  • PDF Parsing
Education

Where I studied

Contact

Get in touch

I'm currently open to new opportunities and collaborations. Whether you have a question, a project idea, or just want to say hi — my inbox is always open.