cv

Basics

Name Ignacio Cuñado Barral
Label Research Assistant in Applied Mathematics & Machine Learning
Email contact@ignaciocunado.com
Phone +34 690877125
Url https://www.ignaciocunado.com
Summary Research Assistant at Delft University of Technology specializing in deep learning on relational data, graph neural networks, and tabular transformers. Recent BSc in Computer Science and Engineering (Cum Laude) with a minor in Mathematics and Statistics. Passionate about leveraging machine learning to solve real-world problems with hands-on experience in Python, Java, C++, and modern ML frameworks.

Work

  • 2025.09 - present

    Delft, Netherlands

    Research Assistant
    Delft University of Technology
    Conducting research on Relational Deep Learning and graph neural networks.
    • Researching Relational Deep Learning by benchmarking Tabular Transformers against state-of-the-art graph learning models (RDL, RelGT, ft-PNA, ft-FraudGT)
    • Investigating graph coarsening strategies to extend applicability to heterogeneous relational graphs
    • Working under supervision of Prof. Kshitij Anan at the Data Intensive Systems Lab
  • 2025.07 - 2025.09

    Rotterdam, Netherlands

    Data Science Intern
    Robeco
    Developed data visualization and attribution analysis tools for ESG and emissions data.
    • Built web-based tool to visualize company hierarchies and emissions data inheritance for 3+ million companies
    • Researched and developed novel attribution method incorporating trading data to measure fund decarbonisation
    • Improved candidate selection pipeline by 50% while lowering inference time
  • 2024.04 - 2024.07

    Delft, Netherlands

    AI Software Engineer Intern
    Lufthansa Group
    Designed microservices for document processing and semantic search using AI/ML.
    • Designed microservice with Django to extract and categorize grant documents using Meta's Llama framework
    • Leveraged vector databases and NER for semantic search and instantiated BERTopic model
    • Exhaustively evaluated models using F1 score with text summarisation, achieving combined score of 0.77
    • Automated search of academic papers and ranked them by relevance with transformers
  • 2024.02 - present

    Heersmerk, Netherlands

    Part-time Software Engineer
    Paro Software
    Developing features for subscription-based payment processing and document management tools.
    • Migrated payment providers for subscription-based tools handling over $10k weekly volume
    • Developed analytics and reporting features for subscription renewals and discounts
    • Automated license-key generation and delivery, reducing wait time from 1 day to 10 seconds
    • Streamlined invoice generation for efficient document access
    • Migrated and refactored medical charity website with 100,000+ monthly visitors

Education

  • 2025.09 - 2026.06

    Delft, Netherlands

    Bridging Program
    Delft University of Technology
    Applied Mathematics
    • Proofs
    • Analysis
    • Real Analysis
    • Optimization
    • Measure and Probability Theory
    • Partial Differential Equations
    • Numerical Methods
  • 2024.09 - 2025.02

    Milan, Italy

    Minor
    Politecnico di Milano
    Mathematics and Statistics
    • Numerical Analysis for Machine Learning
    • Systems and Methods for Big and Unstructured Data Operations Research
  • 2022.09 - 2025.06

    Delft, Netherlands

    Bachelor of Science
    Delft University of Technology
    Computer Science and Engineering
    • OOP
    • Probability Theory & Statistics
    • Linear Algebra
    • Calculus
    • Machine Learning
    • Big Data Processing
    • Data Mining
    • Computational Intelligence
    • Algorithms & Data Structures
    • Algorithm Design

Awards

Skills

Programming Languages
Python
Java
C++
Scala
SQL
HTML/CSS
JavaScript
PHP
Julia
Solidity
Machine Learning & Data Science
PyTorch
TensorFlow
NumPy
Pandas
Scikit-learn
Graph Neural Networks
Deep Learning
Tabular Transformers
Relational Deep Learning
Big Data & Distributed Systems
Apache Spark
Data Processing
Big Data
ETL
Web Development & Frameworks
Django
React
Node.js
Laravel
Spring
Flask
Data Engineering & Tools
Vector Databases
NER
BERTopic
Bash
Git
Docker
Statistical Methods
Bayesian Statistics
Probability Theory
Statistical Analysis
Numerical Analysis

Languages

Spanish
Native speaker
English
Full professional proficiency

Projects

  • 2025.04 - 2025.06
    Graph Learning Methods on Tabular Data
    Researched local and global attention mechanisms for Graph Transformers in Relational Deep Learning.
    • Implemented custom relation-aware local attention mechanisms
    • Achieved state-of-the-art results on classification and regression benchmarks
  • 2024.10 - 2025.02
    Bayesian Clustering of Nations by Educational Performance
    Developed Bayesian approaches to clustering nations using PISA educational dataset.
    • Designed semi-parametric approach and Nested Dirichlet Process
    • Presented findings at Italian Society of Statistics (SIS 2025) in Genoa
  • Tree Biomass Prediction
    Hackathon project developing regression model to predict tree biomass using ensemble methods.
    • Part of Team Epoch at Delft Algorithm Programming Contest