Chleo Elea Hinn

<p>During my apprenticeship as a Data Analyst at Allianz Internal Audit, I independently identified an opportunity to apply Artificial Intelligence to a repetitive task performed by a colleague.</p><p>After understanding the existing workflow and the difficulties associated with the task, I explored how an AI-based assistant could support the process and developed a solution intended to reduce repetitive manual effort.</p><p>The initiative involved identifying a practical business use case, understanding user requirements, translating those requirements into a technical approach, and developing an AI-assisted workflow. It required considering not only the technical implementation but also whether AI was an appropriate solution for the problem.</p><p>Working within a regulated corporate environment also strengthened my awareness of the importance of confidentiality, information security, and responsible use of AI.</p><p>Unlike my personal and academic projects, this initiative was developed in a professional setting and provided valuable experience in connecting technical experimentation with real business needs.</p>

<p>Developed a personal AI application using Retrieval-Augmented Generation (RAG) to explore how Large Language Models can provide more accurate and contextually relevant answers by incorporating information retrieved from external data sources.</p><p>The application combines Python, Ollama with Llama 3, ChromaDB as a vector database, FastAPI for backend functionality, and Streamlit for the user interface. The system retrieves relevant information from a knowledge base and incorporates it into the language model's context before generating a response, reducing reliance on the model's general knowledge alone.</p><p>This project allowed me to gain practical experience with LLM integration, vector databases, information retrieval, API development, and connecting multiple components into a functional AI application. It also strengthened my understanding of how data preparation and retrieval quality influence the usefulness of generative AI solutions.</p><p>The project was independently developed as part of my personal learning and technical development outside my professional responsibilities.</p>

<p>Developed a Python-based data-processing project during my technical studies, with an emphasis on working with different data representations and transforming information into structured outputs.</p><p>The project explores the use of Python scripts to process text-based inputs and work with JSON-formatted data. It provided practical exposure to handling input data, organizing processing logic, and producing outputs that can be used by other scripts or applications.</p><p>Through this academic project, I strengthened my understanding of Python scripting, data structures, and the importance of maintaining consistent data formats when exchanging information between components.</p><p>The project also helped me develop a more practical understanding of how relatively small processing scripts contribute to larger data workflows, where information must be transformed into suitable formats before being stored, analyzed, or passed to another system.</p>

<p>Developed a data-processing project as part of my technical training, focusing on the use of Python and SQL to work with structured datasets and explore the fundamental principles of data engineering.</p><p>The project involved working with data-processing logic, database queries, and the organization of data operations into a structured workflow. Python and Jupyter Notebook were used for developing and exploring the processing steps, while SQL provided the means to interact with relational data.</p><p>The objective was to gain practical experience with the technical foundations of data pipelines, including understanding how information can be retrieved, processed, and prepared for further analysis or use by other applications.</p><p>As an academic learning project rather than a production system, it provided an opportunity to strengthen my programming and database skills, develop a more systematic approach to data processing, and become familiar with technologies commonly used in data engineering.</p>