Ph.D. Data Scientist with 5 years of experience driven by intellectual curiosity, continuing learning, and passion for generating knowledge from data to solve problems and being able to communicate a compelling story.
Programming languages and Tools:
CV ML classifier (XGBoost: gradient boosting) to classify between functional and non-functional molecules. Batch-deployment with Docker and FastAPI.
Building ML Pipeline in PySpark MLlib Perform basic cleaning techniques, then create a ML pipeline (random-forest model). Using cross validation and parameter tuning.
AI model (Deep learning framework: Mask R-CNN from Facebook AI Research) to collect data about crowd flows. This Computer Vision algorithm allows to count and segment people, this project was implemented with:
Feel free to connect with me
E-mail