Working Student - Machine Learning and NLP for Open-Source Intelligence Evaluation (m/w/d)

Working Student - Machine Learning and NLP for Open-Source Intelligence Evaluation (m/w/d)

The Innovation Center (IZ) observes trends in technology and society and serves as an incubator and accelerator for the explorative development of modern business models for the entire IABG Group. The Innovation Center sees itself as the spearhead for industrializing the latest research and putting it to beneficial use for customers. We experiment not only with technologies and methods but also with organizational forms and business models. We are guided by the question of how an increasingly globalized and urban society can be developed in a secure, and sustainable manner, whose organizations and systems are already networked at Internet speed.

We're seeking a motivated working student to support us in the evaluation of Open-source Intelligence (OSINT) tools. OSINT tools have become increasingly important in today's digital landscape, enabling organizations to stay informed about potential threats, opportunities, and trends by leveraging the vast amounts of openly available data. Integrating Machine Learning (ML) into OSINT tools has greatly enhanced their efficiency and accuracy. Key factors for evaluating ML-powered OSINT tools include data quality, model transparency, and ongoing training to ensure reliability and minimize bias. To this end, your job will be to ensure the correct assessment of capabilities via data collection, curation, labeling of OSINT datasets.

You will research existing open-source datasets and benchmarks for NLP tasks related to OSINT, collect quality samples and ground-truth data from various sources, ensure data quality and accuracy through comprehensive validation, and transform raw data into formats suitable for automatic analysis by NLP pipelines.

You will work with natural language corpora, utilizing named entity recognition and semantic analysis techniques to extract meaningful insights from text data. Proficiency in Python is essential for this role, as you will be developing and implementing scripts to automate these processes.

• Researching existing open-source datasets and benchmarks for evaluating common Natural Language Processing (NLP) tasks related to OSINT (e.g. sentiment analysis or named entity recognition)
• Collecting quality samples and ground-truth data from real-world and synthetic data sources, through scraping and other data collection method (API queries, third-party data providers)
• Ensuring data quality according to criteria such as completeness, correctness, comprehensiveness, and the establishment of ground truth to validate the accuracy of the data
• Transform raw data into a format that can be easily analyzed and processed automatically by NLP pipelines
• Good understanding of general ML concepts and methods, and specific concepts related to NLP (LLMs, named-entity recognition, sentiment analysis, speech recognition …)
• Very good programming skills in Python and experience in software engineering, especially for ML-based applications
• Practical experience with Linux CLI and Git. Docker and ElasticSearch is a plus
• Very good communication skills in English and German.

As a working student in our team, you will be part of a division that prides itself on diversity and proficiency, working at the forefront of our organization's transformation. You can expect an exciting and challenging job with a lot of responsibility in a dynamic and innovative environment.