Work Experience
Machine Learning Engineer in Life Sciences
I specialise in the implementation of generative AI pipelines for biotech & pharma companies, helping to improve patient outcomes and develop novel therapeutics with digital innovations.
Business Project Manager
I organize executive innovation courses for senior leaders in the healthcare and pharma industry. I've run 3 different courses with around 15 participants each, working directly with healthcare executives to help them share the knowledge with younger generations of professionals.
Beyond the courses, I help manage our alumni network of 100 members, mostly Portuguese professionals working across Europe and America. I host initiatives that help them share knowledge between them and navigate challenges throughout their careers.
Project Manager
I oversaw the CRUZAMENTO podcast and bootcamp projects by:
- Tracking progress, coordinating with team members, and managing tasks.
- Researching and planning future projects and initiatives.
Acting Data Science Coordinator
Besides executing the day-to-day tasks as a biomedical data scientist, I also planned and managed all data science tasks company-wide, within a framework of sprints. Acting as a bridge between the development team and the product design team, I also identified potential risks or challenges during the spring and worked with the team to mitigate them.
Biomedical Data Scientist
As a Biomedical Data Scientist, I developed products for every stage of the data pipeline — from data acquisition, through data analysis, and ML pipeline deployment.
Being in an early-stage start-up, I had the opportunity to contribute in several domains: project planning and managing, experimental protocol design, managing internships, and external company representation.
Data Scientist Intern
Throughout this one-year internship, I developed my master's thesis entitled "Transfer Learning Techniques for Classification of Biological Samples using Optical Fingerprint". My main contributions were:
- Exploration of techniques to mitigate the influence of confounding clinical factors in the classification task;
- Exploration of different 2D representations of time series data, both static and dynamic encodings;
- Development of an end-to-end deep learning pipeline for the encoding and classification of time-series data.
Volunteering Data Scientist
Volunteering project where an international team of data professionals is developing an AI-powered app that utilizes predictive modeling and forecasting techniques to enhance malaria prevention efforts in Liberia. Link to project.
Research Intern
During my Erasmus+ program, I studied the hypothesis that the brain structural changes with aging, already reported in humans, are similar to those in the common marmoset. Before my internship, the longitudinal segmentation of the marmoset brain in the research institute was a time-consuming task done manually, which I automatized, creating an end-to-end standardized pipeline. Using mixed-effects modeling, I analyzed the relation between several clinical variables in a longitudinal study.
Data Scientist Intern
While learning the first concepts of machine learning in the 1st year of my master's degree, I was getting hands-on experience in a consultant firm. In 5 months, I developed a live demo to show new clients the potential of a content retrieval system powered by Artificial Intelligence. Link to blogpost.
Research Trainee
My first contact with a working environment was during the 2nd year of my Bachelor's degree. During this internship, I assessed which frequency domains are the best for detecting fetal acidemia, starting with a systematic literature review, followed by the evaluation of fetal heart rate traces using several signal-processing techniques and performing an extensive statistical analysis of the key results. This work resulted in an abstract presented at the 48th Neonatology Congress (Lisbon, 2019) and an article published in the journal Frontiers in Pediatrics. Link to paper.