Marin Hure

Utilized Retrieval-Augmented Generation (RAG): Employed RAG to dynamically access and retrieve relevant documentation from the developed Python framework for data quality, enhancing the LLM's ability to generate accurate and context-aware functions. Integrated Large Language Models (LLMs): Leveraged LLMs to convert natural language queries into executable Python code for data validation. Supported multiple data processing engines: Integrated with both Pandas and Spark engines for flexible data processing and validation.

Developed a SLAM (Simultaneous Localization and Mapping) tool to assist visually impaired individuals in navigating spaces. - Implemented SLAM algorithms for accurate localization and mapping. - Applied machine learning models to SLAM point cloud outputs for object detection. - Utilized Git for version control and collaboration. - Integrated the system into a user-friendly application for real-time assistance.