Master Thesis: Generative AI in practice
Om jobbet
Join our Team
About this opportunity:
Modern mobile networks generate vast telemetry, logs, traces, and performance metrics. Traditional dashboards and alarms provide visibility, but growing RAN complexity calls for systems that turn data into clear, actionable insights. AI techniques like transformers, semantic search, and graph reasoning now make it possible to build assistants that detect issues and explain their causes with evidence.
What you will do:
The goal of this thesis is to design and evaluate a semantic reasoning assistant for RAN assurance. The assistant will combine lightweight transformer models for semantic search/embedding and classification with large generative models for natural-language explanation and graph databases for causal reasoning. The work will focus on prediction and analyzes of incidents, answering "what/how/why" questions and correlating events across heterogeneous data sources.
The following steps are envisioned:
• Investigate state-of-the-art methods in semantic embeddings, retrieval-augmented generation, and graph-based reasoning.
• Implement a pipeline combining embeddings, vector search, graph modeling, and LLM-based explanation.
• Use synthetic or anonymized RAN data to evaluate the system.
• Benchmark accuracy, explanation quality, and transparency compared to baseline observability tools.
• Present a prototype and results to Ericsson researchers.
The skills you bring:
This project is suitable for students in computer science, data science, AI science, with interest in:
• Artificial Intelligence (transformer models, semantic search, large language models)
• Data Management (graph databases, vector databases, large-scale data handling)
• Telecom Networks (Cloud RAN, observability, assurance)
Why join Ericsson?
At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply?
Click Here to find all you need to know about what our typical hiring process looks like.
Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city:
Sweden (SE) || Stockholm
Req ID:
773524
About this opportunity:
Modern mobile networks generate vast telemetry, logs, traces, and performance metrics. Traditional dashboards and alarms provide visibility, but growing RAN complexity calls for systems that turn data into clear, actionable insights. AI techniques like transformers, semantic search, and graph reasoning now make it possible to build assistants that detect issues and explain their causes with evidence.
What you will do:
The goal of this thesis is to design and evaluate a semantic reasoning assistant for RAN assurance. The assistant will combine lightweight transformer models for semantic search/embedding and classification with large generative models for natural-language explanation and graph databases for causal reasoning. The work will focus on prediction and analyzes of incidents, answering "what/how/why" questions and correlating events across heterogeneous data sources.
The following steps are envisioned:
• Investigate state-of-the-art methods in semantic embeddings, retrieval-augmented generation, and graph-based reasoning.
• Implement a pipeline combining embeddings, vector search, graph modeling, and LLM-based explanation.
• Use synthetic or anonymized RAN data to evaluate the system.
• Benchmark accuracy, explanation quality, and transparency compared to baseline observability tools.
• Present a prototype and results to Ericsson researchers.
The skills you bring:
This project is suitable for students in computer science, data science, AI science, with interest in:
• Artificial Intelligence (transformer models, semantic search, large language models)
• Data Management (graph databases, vector databases, large-scale data handling)
• Telecom Networks (Cloud RAN, observability, assurance)
Why join Ericsson?
At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply?
Click Here to find all you need to know about what our typical hiring process looks like.
Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city:
Sweden (SE) || Stockholm
Req ID:
773524
Ericsson AB
FöretagEricsson AB
Visa alla jobb för Ericsson AB