Master Thesis AI Efficient Compute RBS

Join our Team

Ericsson Overview

Ericsson is a world-leading provider of telecommunications equipment and services to mobile and fixed network operators. Over 1,000 networks in more than 180 countries use Ericsson equipment, and more than 40 percent of the world's mobile traffic passes through Ericsson networks. Using innovation to empower people, business and society, Ericsson is working towards Networked Society: A world connected in real time that will open up opportunities to create freedom, transform society and drive solutions to some of our planet's greatest challenges.

We are truly a global company, operating across borders in over 180 countries, offering a diverse, performance-driven culture and an innovative and engaging environment. As an Ericsson employee, you will have freedom to think big and the support to turn ideas into achievements. Continuous learning and growth opportunities allow you to acquire the knowledge and skills necessary to progress and reach your career goals. We invite you to join our team.


Position summary

Considering the demand for new network capabilities, and requirements for high precision operations, AI/ML based solutions provide an opportunity to evolve the network in specific directions. By utilizing Graph neural network techniques, such Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), Message Passing Neural Networks (MPNNs) and Graph Recurrent Networks (GRNs) network element performance can be improved.

In this study, considering the set of technics that can be used, the study shall investigate to prioritize energy efficiency recommendations without sacrificing energy usage, and Quality of service (latency, throughput).

The thesis is suitable for one student and would involve the following steps (can be suited adjusted to research interest of the candidate).

• Literature review: Identifying relevant concepts and algorithms for telecommunications.
• Enable a network view of all entities to secure right metrics.
• Apply: Suitable AI/ML algorithms, modeling and implementation into the network. A chosen techniques for the selected use case
• Evaluation and test: Obtain model for the considered use case from network perspective

Qualifications

We are looking for a highly motivated student who seeks challenging research work with the freedom to propose and develop new ideas. To be successful in this thesis work, the candidate would need the following:

• MSc studies in Computer Science, Mathematics, Physics, Engineering fields or similar areas.
• Excellent programming skills in Python.
• Good knowledge of concepts in machine learning (including deep learning) and other AI technics.
• Experience with machine learning libraries such as TensorFlow, Keras, PyTorch, Scikit-Learn, Spark, etc.
• Knowledge of docker containers, Cloud, orchestration systems, and telecommunications is a bonus.
• Like to build end-to-end prototypes and concepts.
• Be fluent in English

Available soon at ericsson.com/careers

Contact Person: Aneta Vulgarakis aneta.vulgarakis@ericsson.com

Supervision: Lackis Eleftheriadis lackis.eleftheriadis@ericsson.com ; Oleg Gorbatov oleg.gorbatov@ericsson.com