Computer scientist - Real time data fusion

C+, + CI/CD (Continuous Integration/Delivery) CMake Docker Forschung

+6 Top

At the Institute for the Protection of Maritime Infrastructures in Bremerhaven, we research and develop innovative solutions to strengthen the resilience of maritime infrastructures and make them adaptable, safe and sustainable. In close cooperation with partners from research, industry and other maritime security stakeholders, we combine technological innovation with practical expertise and offer you the opportunity to work on pioneering projects.

What you can expect

As a new team member in the Situational Awareness and Cybersecurity Group within the Maritime Security Technologies Department, you will research and develop innovative methods for fusing underwater acoustic data from fibre-optic sensors (DAS) with vessel movement data from AIS, satellites, drones and radar systems. Your work will aim to detect security anomalies in the maritime domain at an early stage and integrate these into a combined surface and underwater situational picture.

You will plan and implement research projects to develop and evaluate AI-based algorithms for anomaly detection in heterogeneous, spatially and temporally distributed sensor data. In doing so, you will utilise unsupervised learning, autoencoders, isolation forests and active learning to identify even unknown threat patterns in near real time.

Through your work, you will actively contribute to the creation of a robust, adaptive and decision-supporting situational awareness system for maritime infrastructure - directly linking fundamental research, technological innovation and practical application. We would be happy to offer you the opportunity to use these topics for a PhD., * Designing and conducting research on the fusion of DAS acoustic data and vessel movement data (AIS, satellites, radar, drones) to detect security anomalies in the maritime domain

• Developing and implementing AI models for anomaly detection in time series and geospatial data, in particular using unsupervised learning, autoencoders and active learning
• Carrying out data preparation and fusion from heterogeneous sources (DAS, AIS, satellites, radar), including temporal and spatial alignment as well as data quality control
• Validating the models using datasets from field experiments and long-term measurements
• Publishing the results at international conferences

• A completed academic degree (Master's / Diploma) in Computer Science, Software Engineering or another relevant discipline
• Strong knowledge of machine learning, particularly unsupervised learning, anomaly detection, time series analysis and their application to sensor data, for example data from DAS or other hydroacoustic systems
• Experience in developing efficient algorithms and data structures for data-intensive real-time applications
• Practical experience in sensor data fusion, the analysis of large, heterogeneous datasets, and the integration of geodata and time series into geographic information systems (GIS) or real-time data pipelines
• Programming skills in C++ and Python, as well as experience with data structures, algorithms, software architectures and development tools (e.g. CMake, Git, Docker, CI/CD)
• Initial scientific publications or presentations in the field of AI and data fusion
• Good written and spoken English, as well as the ability to communicate complex research findings clearly and precisely

DLR stands for diversity, appreciation and equality for all people. We promote independent work and the individual development of our employees both personally and professionally. To this end, we offer numerous training and development opportunities. Equal opportunities are of particular importance to us, which is why we want to increase the proportion of women in science and management in particular. Applicants with severe disabilities will be given preference if they are qualified.