Master Thesis: Agentic AI for telecom

Join our Team
About this opportunity:
Ericsson is looking for four Master's thesis students to work on emerging areas of Agentic AI for telecom applications. Agentic AI systems can reason, use tools, access data, collaborate with people and other agents, and perform multi-step tasks across enterprise systems.
Each student will focus on one of four thesis areas:
1. Agentic AI Security
Best practices for securely integrating AI agents with enterprise data, tools, APIs, and systems, with a focus on authentication, authorization, delegated access, identity, and accountability for agent actions. Presenting misuse, data leakage an unauthorized actions.
2. Collaborative AI Spaces
How should environments be designed where people and multiple AI agents share context, delegate tasks, retain knowledge, and solve engineering problems together?
3. Fine-Tuning & Domain Adaptation
How can general-purpose language models be adapted for specialized telecom knowledge and reasoning, and when is fine-tuning more effective than Skills, RAG, prompting, or tool use?
4. Agentic AI Evaluation
How can we measure whether AI agents perform complex tasks correctly, reliably, safely, and efficiently across multi-step workflows?
The theses will combine research with hands-on development, prototyping, and experimentation using modern LLM and agentic AI technologies.
What you will do:- Investigate one of the four Agentic AI research areas.- Review relevant research and emerging industry approaches.- Build full-stack prototypes using LLMs, agents, RAG, tools, APIs, and enterprise data.- Develop backend services and user interfaces for experimental AI systems.- Design experiments and systematically evaluate different approaches.- Work with telecom engineers, AI specialists, data scientists, and architects.- Produce practical recommendations based on your research findings.
The skills you bring:- Currently pursuing a Master's degree in Computer Science, AI, Data Science, or a related field.- Strong programming skills in both Python and JavaScript or TypeScript.- Experience developing software applications through coursework, projects, internships, or research.- Understanding of APIs, web applications, databases, and software development fundamentals.- Interest in LLMs, generative AI, and agentic systems.- Ability to design experiments, analyze results, and build working prototypes.- Collaborative, self-motivated, and eager to explore emerging technologies.
Preferred qualifications:Experience with one or more of the following is beneficial:- Python backend frameworks such as FastAPI.- JavaScript/TypeScript frontend frameworks such as React, Svelte, or similar.- Agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or similar.- RAG, vector databases, knowledge graphs, or embeddings.- PyTorch, Hugging Face, LoRA, QLoRA, or other model fine-tuning approaches.- AI security, authentication, authorization, or adversarial testing.- LLM evaluation, automated testing, benchmarking, or experiment tracking.- AWS, Azure, Docker, Kubernetes, CI/CD, or cloud-native development.
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: 790843