About this opportunity:
Are you ready to take on the challenge of designing and evaluating the next generation of multi-agent AI systems? This master’s thesis explores the design, orchestration, and evaluation of multi-agent AI architectures for solving complex, real-world problems in telecom systems. You will investigate how specialized AI agents—each with unique capabilities—can collaborate effectively through structured communication, shared context, and adaptive task allocation. The goal is to create a modular, extensible framework where agents can reason together, delegate work, and integrate with both internal tools and external APIs to deliver coherent, end-to-end solutions.
What you will do:
- Research state-of-the-art multi-agent system designs and coordination strategies
- Define and prototype agent roles (e.g., planner, retriever, reasoner, executor) with clear capability boundaries
- Explore communication patterns such as message passing, shared memory, and protocol-based contracts (e.g., MCP)
- Implement orchestration mechanisms using frameworks like LangGraph, CrewAI, AutoGen, or OpenAI Assistants
- Integrate retrieval-augmented generation (RAG), embedding stores, and runtime introspection to enable contextual collaboration
- Benchmark system performance on telecom-relevant tasks such as fault diagnosis, configuration optimization, and automated reporting
The skills you bring:
- Currently enrolled in a Master’s program in Computer Science, AI, or a related field
- Strong Python and JS programming skills and familiarity with AI/ML frameworks
- Interest in distributed AI, agent-based reasoning, and orchestration techniques
- Understanding of LLM APIs, embedding models, and retrieval systems is a plus
- Ability to work with both structured and unstructured data, and to translate requirements into modular system components
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?