Senior Data Scientist (PhD in Computer Science)

As a Data Scientist in the Map Advanced Analytics team at TomTom, I focus on generating new metrics and insights to enhance the quality and development Lane Model Maps. My role involves: • Design and implement customer-facing quality metrics for Lane Model Maps, establishing the key performance indicators (KPIs) used by engineering teams to prioritize development and by sales to demonstrate product superiority to clients. • Own the end-to-end ETL process for complex geospatial data, utilizing PySpark and Python on Databricks to compute metrics, reducing data processing latency and improving data reliability for cross-functional teams. • Leveraging Databricks, PySpark, QGIS, and Python to compute and analyze geospatial and map quality metrics. • Engineer and deploy an interactive Streamlit dashboard to visualize core map quality metrics, empowering non-technical stakeholders and decision-makers to perform self-service analysis and monitor progress in real-time. • Develop and optimize methodologies for assessing high-definition map layers using QGIS and GeoPandas, enhancing the accuracy and scalability of the map quality evaluation framework.

As a Visiting Researcher and Data Scientist, I've been immersed in an intensive 3-month research collaboration with DLR in Berlin. My efforts were geared towards: • Led urban traffic management projects using Python, GIS, GeoPandas, and machine learning methods, contributing to the development of sustainable city planning frameworks by optimizing vehicle traffic flows. • Applied statistical models and machine learning algorithms to analyze large datasets and study environmental impacts, providing data-driven recommendations to support sustainable urban development. • Integrated external data sources and developed geospatial and predictive models using Python and Scikit-Learn for forecasting urban pollution levels, aiding policymakers in implementing effective environmental measures. • Conducted performance monitoring and evaluation of traffic management models, identifying data drifts, deploying model updates, and optimizing model accuracy by refining data inputs and parameters.

As a Data Scientist and Researcher with a predoctoral grant from the Universitat Politècnica de València, I've worked in the Networking Research Group (GRC) of the Computer Engineering Department (DISCA). My responsibilities include: • Developed and implemented Python-based algorithms and machine learning models for optimizing pollution-impacted vehicle routing, improving urban traffic efficiency by 20% through advanced statistical analysis and regression techniques. • Designed and maintained data pipelines using Python and SQL for data cleaning, processing, and ETL, enabling the efficient organization of large experimental datasets for research and development purposes. • Collaborated with international research teams to present findings at conferences and contributed to scientific publications on data science and traffic management, enhancing the academic community’s understanding of urban planning and data-driven solutions. • Conducted in-depth data analysis and built predictive models using Python, Matplotlib, Seaborn, and Scikit-Learn on traffic pattern datasets, generating actionable insights and reports that influenced city planning and policy development. • Developed data-driven research proposals and presentations, leveraging machine learning techniques to improve the clarity and impact of complex traffic and environmental data for academic and public stakeholders.