Yasmine Masmoudi

- Designed, built, and optimized scalable PySpark data pipelines to support efficient data ingestion, transformation, and delivery across the full data lifecycle. Contributed to end-to-end solutions, from integrating heterogeneous data sources to enabling real-time, insight-driven applications. - Supported and maintained Palantir Foundry applications, handling incident resolution, monitoring pipeline performance, and ensuring alignment between technical performance and business requirements. - Collaborated closely with cross-functional teams (data engineers, product owners, and business stakeholders) to develop internal tools and data-driven applications that translate analytics into operational workflows, automated actions, and measurable business impact. - Participated in the design of scalable data architectures, optimizing workflows and improving data quality, reliability, and accessibility to enhance decision-making through advanced analytics and automation. Key Focus Areas - Palantir Foundry: data integration, pipeline development, ontology design, and application deployment. - Data Engineering & Strategy: designing and optimizing scalable data workflows for performance, reliability, and business value.

- Semiconductor production process (wafer production and testing, device packaging and final testing) - Developing and testing a tool to correlate between semiconductor technology parameters and final post silicon test data.

- Creating a deep learning model to address the NILM (energy disaggregation) problem. - Applying MLOps best practices, such as experiment tracking, model management, and workflow orchestration in order to enhance the model's lifecycle development.

- Conceptualized and simulated a custom map for autonomous robot navigation using the WeBots environment, Java Open Street Map, and SUMO traffic simulation software. - Implemented a deep reinforcement learning algorithm to enable the robot to navigate the map and make deliveries autonomously using the Deepbots package.