Senior Data Engineer ING WBAA — Amsterdam Area, Netherlands · Hybrid Apr 2023 — present

• Technical leadership: technical lead for the team’s data engineering work — architecture decisions, code quality, production ownership and incident resolution, migration planning and cross-team knowledge sharing
• Data products & regulatory delivery: designed and operated business-critical KYC/CDD and regulatory data products (SEPA, SWIFT, accountability); built and optimized ETL pipelines with PySpark and Airflow; kept pipelines healthy through recurring framework upgrades (Airflow v2→v3, PySpark v4)
• Cloud migration & platform engineering: led the data-pipeline workstream of the migration from on-premise (DAP) to ING’s Vista/GCP platform — architecture, cloud-native storage (BigQuery, GCS), orchestration (Cloud Composer) and security patterns; contributed to IaC adoption with Terraform; evaluated migration-ready design via a Kedro + Ibis PoC that shaped tooling decisions
• Community & speaking: speaker at TechFest/DECONF (“Kedro + Ibis: Is This the End of Painful Data Pipeline Migrations?”), member of the DECONF organizing team; contributed to hiring via technical interviews and interviewer onboarding

Senior Data Scientist ING WBAA — The Randstad, Netherlands Feb 2019 — Apr 2023

• Hunter (AML investigation platform): ML features and analytics for ING’s anti-money-laundering investigation platform — entity resolution, country extraction and scalable fuzzy matching in Spark over millions of names, reducing false positives; led weak-supervision research (WeaSUL: Snorkel-based data programming) enabling label creation in low-ground-truth environments
• CodeFix (AI-assisted software security): sole data scientist in the early phase — shaped the product’s technical direction, defined the DS roadmap and established academic collaborations; built PoCs on Fortify scan data and applied NLP (word2vec, BERT-based) to source-code comprehension and vulnerability-detection false-positive reduction
• Holmes document search: led deployment of a production-grade named entity recognition model powering ING’s document search
• Model deployment & MLOps: productionized ML models as scalable services with Docker and FastAPI; built deployment pipelines on Kedro and Airflow; helped establish machine learning engineering practices in ING Analytics; co-presented ING’s MLOps strategy at the MLE Guild and delivered workshops on MLflow, Docker and production ML
• Research supervision & mentoring: co-supervised MSc research on weak supervision and active learning for financial-crime analytics; mentored junior data scientists and trainees across WBAA

Data Scientist Corl Financial Technologies — Toronto, Canada Mar 2018 — Nov 2018

I was involved in the process of building predictive models for investment risk in startups. The process involved:

• Retrieving data from different sources, including scraping data from the web (using Selenium with Beautiful Soup)
• Analysing data using Jupyter notebooks, pandas and matplotlib
• Building machine learning models using Random Forest and SVM to fit our prediction problems
• Feature selection/engineering

Project Manager Universidade Federal de Minas Gerais — Belo Horizonte, Brazil Mar 2018 — May 2018

Project Manager on the EU-Brazil project ATMOSPHERE. I managed resources, followed the status of deliverables and delegated activities for three Brazilian universities: UFMG, Unicamp and UFAM.

Contributing Researcher Universidade Federal de Minas Gerais — Belo Horizonte, Brazil Aug 2017 — Jan 2019

I worked on two different projects with the LaIC (Computational Intelligence Laboratory) research group:

1. Reducing the exponential size of solutions generated by the Geometric Semantic Genetic Programming (GSGP) framework, in order to improve their interpretability and reduce memory and computational cost.
2. Analysing datasets used as benchmark for Genetic Programming (GP)-based methods under a data science perspective: gathering datasets employed by the main GP publications of the last five years and analysing the viability of using GP to induce regression models.

Postdoctoral Researcher University College Cork — Cork, Ireland Aug 2017 — Dec 2017

I worked on the development of autonomous tugs, capable of towing aircraft on the airport ground — from the runway to the gates during arrivals, and vice versa during departures.

• Surveyed current advances in autonomous vehicles and worked on optimization of ground routes in airports
• Worked in coordination with United Technologies
• Worked with Python (built a parser for XML airport maps) and Java/CPLEX (route optimization)

Postdoctoral Researcher Universidade Federal de Minas Gerais — Belo Horizonte, Brazil Oct 2016 — Aug 2017

I worked with Geometric Semantic Genetic Programming (GSGP) on two main projects:

1. A study investigating aspects related to the semantic distribution of the functions employed by geometric semantic operators;
2. An investigation of the impact of different instance selection techniques on GSGP and its robustness to noisy data.

This included managing a research team of three researchers, and development in Java (genetic programming framework), R (hypothesis tests and plotting) and shell script (text/data manipulation).