• Since March 2021
    Data Scientist
    adidas | Amsterdam, The Netherlands
    • In the Digital Data Science org, I am part of a team responsible for creating data science solutions that enable trading excellence throughout adidas eCom business (.com and apps). My main responsabilities have been
      • Developing production-ready machine learning models that forecast demand for thousands of adidas products (PyTorch).
      • Building and maintaining highly scalable, robust, cloud-native machine learning pipelines deployed on AWS (SageMaker Pipelines that orchestrate training, inference, and processing steps; EMR; Step and Lambda functions).
      • Integrating MLOps components into the forecasting products (e.g., automated model monitoring).
      • Developing CI/CD pipelines (Jenkins), unit tests (PyTest), code quality checks (PyLint, Black), integration tests.
      • Optimizing big data processing workflows (PySpark).
      • Collaborating closely with adidas' Buying, Planning, and Trading teams to promote adoption of our products and ensure their impact.
      • Rolling out products to new users and markets.
      • Streamlining data science tools and way of working.
  • Jan 2020 - Feb 2021
    Data Scientist
    FIOD - Belastingdienst
    • In my 12-month-project with FIOD-Belastingdienst, I worked on the following tasks in collaboration with FIOD's data science team (CoDE)
      • Developed custom object detection and image classification models using TensorFlow and deployed them as REST APIs using Flask and Docker.
      • Created a web application for the end-users - FIOD Image Intelligence - written in JavaScript, NGINX, D3.JS, MapBox.
  • 2019-2021
    Engineering Doctorate Candidate in Data Science
    Eindhoven University of Technology | Eindhoven, The Netherlands
    As a trainee in the EngD Data Science, I worked on the following 7 projects:
    • ASML | “Unsupervised Particle Identification in Reticle Images”
      • Implemented image segmentation strategies to identify particles in high-resolution reticle images.
    • Heijmans | “Prediction of Occupancy in Working Spaces Using Sensor Data”
      • Developed an end-to-end neural network model for predicting the occupancy in different zones/desks.
      • Created embeddings for categorical features.
    • Van Lanschot | “Detection of Suspicious Cases of Money Laundering”
      • Tested a community-oriented approach for identification of suspicious cases of money-laundering from transaction data.
      • Developed an application for visualizing the transaction network graph and the suspicious communities extracted.
    • Den Bosch Municipality | “Solar Scan - Solar Potential Assessment from Satellite Images”
      • Built a CNN model for segmentation of building rooftops in satellite images and use the output to assess solar potential of buildings.
      • Developed a web app to visualize the results.
    • TE Connectivity | “Recommendation System for Product Cross-Sell”
      • Implemented a product recommendation system based on low-rank matrix factorization for thousands of parts using global sales data.
      • Developed a web application to display the product recommendation scores.
    • ASML | “Analyzing the Part Lifecycle in the Supply Chain Process at ASML”
      • Analyzed the lifecycle of spare parts using process mining and identified its bottlenecks.
      • Proposed an approach to identify abnormal part movements using association rule mining.
    • Coaching/supervision:
      • Introduction to Data Science course at TU/e.
      • Data Science in Health Program at JADS.
  • Jan 2019 - Jul 2019
    Lab Monitor
    Lisbon Machine Learning School (LxMLS) | Lisbon, Portugal
    • Part of the organizing team of LxMLS'19 as a monitor.
    • Had responsibilities in the organization of the school and helped the students solving the exercises during the lab sessions, implementing machine learning algorithms such as hidden Markov models, conditional random fields, recurrent neural networks, and reinforcement learning.
  • Jan 2018 - Dec 2018
    Student Researcher
    Institute for Systems and Robotics | Lisbon, Portugal
    • Within the Signal and Image Processing group of ISR my research focused on deep learning and anomaly detection in time series data.
    • Proposed an approach for time series anomaly detection based on variational autoencoders, recurrent neural networks, and attention mechanisms. This approach is unsupervised, making it suitable for applications where obtaining labels is expensive or time-consuming (fraud detection, medical diagnosis, fault detection, ...).
  • Jul 2017
    EDP | Lisbon, Portugal
    • Built a neural network-based model to forecast the power load in hundreds of electrical substations within the Planning Department of EDP.
  • Jul 2016
    EDP | Coimbra, Portugal
    • Worked on the design of medium/low voltage networks within the Network Studies team.


  • 2019-2021
    EngD, Data Science
    Eindhoven University of Technology | Eindhoven, The Netherlands
  • 2016-2018
    MSc, Electrical and Computer Engineering
    Instituto Superior Técnico | Lisbon, Portugal
  • 2013-2016
    BSc, Electrical and Computer Engineering
    Instituto Superior Técnico | Lisbon, Portugal

Honors and Awards

  • 2017-2018
    • Diploma for Academic Excellence

Academic Interests

  • Machine Learning
  • Anomaly Detection

Other Interests

  • Fitness