Pedro Balage is an Associate Director of Machine Learning Engineering with a PhD in Artificial Intelligence and 13 years building production ML and data science teams across e-commerce, AI data platforms, and consumer travel. He combines deep research expertise in NLP, computer vision and neural retrieval with hands-on delivery of product roadmaps, data architectures and cross-functional stakeholder alignment. He has led and scaled teams at Farfetch, Defined.ai, PandaDoc and now Tripadvisor, applying graph-based similarity, entity linking, taxonomy design and visual attribute extraction to real-world product and search problems. Pedro also founded a consumer review analytics startup and contributes practical test automation to ML education tooling, demonstrating a blend of entrepreneurship, quality engineering and pedagogy. Based in Lisbon, he pairs academic rigor with a product-first mindset to move novel neural architectures from prototype to production.
13 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at USP - Universidade de São Paulo
Postgraduate, Marketing, Strategy & Innovation, Postgraduate, Marketing, Strategy & Innovation at Nova School of Business and Economics
Master of Arts - MA, Natural Language Processing, Master of Arts - MA, Natural Language Processing at University of Algarve
Master of Arts - MA, Natural Language Processing, Master of Arts - MA, Natural Language Processing at University of Wolverhampton
ERASMUS Student, Computer Engineering, ERASMUS Student, Computer Engineering at University of Lisbon
Machine Learning applied to Natural Language Processing Toolkit used in the Lisbon Machine Learning Summer School
Role in this project:
QA Engineer / Test Automation Engineer
Contributions:3 reviews, 46 commits, 8 PRs in 1 year
Contributions summary:Pedro's commits primarily involve adding and modifying test files, specifically focusing on integration tests. The changes include setting up test fixtures, writing test cases, and verifying the expected outputs of functions within the lxmls-toolkit. The tests cover aspects of the toolkit related to deep learning, specifically RNNs and LSTM models, and ensuring the correctness of the exercises within the Lisbon Machine Learning Summer School.
Contributions:2 PRs, 59 pushes, 4 branches in 4 years 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.