Master Thesis: AI Code Knowledge Bases for Onboarding - Designing a Guided Ramp-Up Experience

## Join our Team

About this opportunity:

Getting a new engineer productive in a large, unfamiliar codebase is slow: much of the first weeks go into finding where things are, how components fit together, and why the code is shaped the way it is. AI code knowledge bases — structured knowledge about a codebase's architecture, interfaces, and design intent — hold much of what a newcomer needs, but a knowledge base is not an onboarding experience.

This thesis designs and builds that experience: the flow, the interface and the guided tasks that take a newcomer from first day to first real change, grounded in the code and in what senior engineers know but rarely write down. You will then put it in front of newcomers and find out where it works.

What you will do:

• Study how newcomers ramp up in a large codebase today: the questions and blockers that dominate their first weeks.
• Design the onboarding experience on top of a code knowledge base: entry points such as "how does X work" and "where do I start", navigation through architecture and interfaces, and task-oriented explanations that answer the question actually being asked.
• Build it as a working prototype — the interface and the path a newcomer moves through, from first orientation to first real task, with guided self-check questions, small walkthrough exercises, and visible progress. Game-like elements are welcome where they earn their place.
• Work out what the knowledge base must contain, and in what form, for this to work — and feed the gaps back into how knowledge bases are generated.
• Try it with newcomers and iterate where they get stuck, which explanations land, what they still ask an experienced developer.
• Track a few light measures alongside (comprehension self-checks, tasks completed without escalating, confidence).
• Deliver the prototype and evidence-based recommendations for onboarding at scale.

The skills you bring:

• Currently pursuing a Master's Degree in Computer Science, Software Engineering, Data Science, or a similar field.
• Solid Python; comfort with LLM/agent tooling and with reading real source code.
• Interest in developer experience and in designing something people actually want to use.
• Able to build a usable prototype — web UI, IDE extension or CLI.
• Willingness to test ideas on real users, take the feedback, and iterate.
• Familiarity with retrieval-augmented generation (RAG) and AI coding assistants is a plus.
• Experience with cloud AI/ML services (AWS or similar) is a plus.

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: 791141