Vienna, Vienna, Austria
I am a Scientist in the Data Science & Artificial Intelligence research group at the AIT Austrian Institute of Technology. I am working at the intersection of the humanities and computer science—which began with a PhD in Digital Humanities from the University of Cologne (2006), where I focused on applying fuzzy logic to archaeology. Having a multidisciplinary background in Computer Linguistics, Philosophy (logic, ethics) and Romance languages (Spanish, French), I have spent over a decade developing machine learning solutions for large-scale text analysis within the public security and archival domains. Drawing on my experience across numerous Austrian and EU research projects, I served as the Technical Coordinator for the European Commission’s eArchiving initiative, focusing on trusted repositories and the application of eIDAS. My current research concentrates on Trusted and Responsible AI. I am particularly interested in leveraging semantic web technologies and knowledge graphs to improve the reliability of generative AI systems, with a focus on ethical safeguards, environmental sustainability, and the societal impact of AI deployment. Research interests: ➤ Local Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) systems, ➤ Integration of local large language models with knowledge graphs and semantic technologies, ➤ Application of regulatory guidance to generative systems, ➤ Development of reliable, ethical, and sustainable AI architectures, ➤ Optimization of agent-based coding workflows through multi-model experimentation and evaluation, ➤ Trusted and Responsible AI.
As a Scientist at AIT Austrian Institute of Technology I am working as a project manager, researcher, and developer in international research projects and in commercial software development projects (contract research). My main research interest lies in the application of data mining and natural language processing (NLP) technologies in the context of large digital document collections and archives. In my current role I am involved in project management, proposal writing and software development and my main programming languages are Python, Java and Scala. Regarding technologies I am familiar with large-scale data processing platforms, such as Hadoop and Spark, NLP frameworks such as NLTK or SpaCy, and machine learning frameworks, such as scikit-learn and keras.
From 2008 to 2010, I was participating in the European project PLANETS, mainly as a web service developer integrating file format migration and analysis tools by creating JAX-WS web services deployed on a JBoss application server. From 2008 to 2011 I was participating in the European project IMPACT responsible for the design and development of an interoperability framework using load balanced web services deployed on a distributed cluster using mainly Apache components like Apache Tomcat, Apache Synapse, Apache Axis2. Between 2011 and 2013 I participated in the Austrian Books online project, a large scale book digitisation project in collaboration with Google. I was responsible for creating quality assurance components in a web application framework based mainly on Spring, Hibernate, JSF2.0, and MySQL. At the same time was leading a sub-project in the European Project SCAPE which was dealing with large scale data processing and analysis based on Apache Hadoop.
As an SAP FI Support Consultant I was responsible for the analysis of customer issues in the area of assets management (FI-AA), analysis of errors related to database inconsistencies, and debugging of customer specific Java/ABAP code.
Porting a document management server to Linux (C++) and writing guidelines for Linux development and maintenance; participation in the development of a java web client (J2EE, JavaServer Faces, SOAP, XML/XSLT) for the document management server.
Relational database design and maintenance (MySQL); development of a content and document management system (HTML/CSS/PHP/ Ajax(JavaScript/XML)/ XSLT); deployment and customizing of a search engine (ht://Dig); specification and implementation of XML based data synchronization with partner institutions.