The Opportunity

We are looking for a master thesis student at our R&D department, would like to join our multinational organization with lots of development opportunities. Our team is dedicated to creating a future where innovative digital technology brings cleaner energy to people around the world. If this opportunity excites you, we encourage you to apply!

How you'll make an impact

• Create a simulation setup that accurately replicates a high-density mesh network environment.
• Create processes to collect data from various network nodes in the simulation environment, paying attention to factors such as packet timing, the order in which packets arrive, and any shifts in connectivity.
• Design statistical models to establish what normal network behavior looks like. These models will be key in detecting anomalies, which may reveal potential link failures.
• Design and train machine learning models to anticipate and categorize link failures by analyzing the statistical elements of network data, particularly through packet timing and the order of arrival. This initiative involves investigating multiple supervised and unsupervised techniques for failure detection and anomaly classification.
• Test and optimize the detection strategy's accuracy, efficiency, and robustness across a range of network configurations and traffic conditions. This process includes adjusting model parameters and enhancing detection performance to minimize both false positives and negatives.

• Bachelor's degree in electrical engineering, computer science, data science, or a related field.
• Prior experience in network simulation, data analytics initiatives, or the use of machine learning for network health monitoring would be a valuable asset.
• Proficient in Matlab and Python, or related languages like R, with a solid background in network simulation libraries, including NetworkX, and machine learning libraries like TensorFlow, PyTorch, or scikit-learn.
• Basic understanding of network protocols, topologies, and communication principles, particularly in wired communication systems.
• Knowledge of core machine learning algorithms, encompassing both supervised and unsupervised learning, paired with an awareness of neural networks and strategies for anomaly detection.
• Knowledge in statistics, including familiarity with statistical anomaly detection techniques and experience in data feature engineering.