Master thesis: AI solutions

Join our Team About this opportunity: Software and system architecture must comply with mandatory architecture requirements and design principles to support secure, scalable, and maintainable solutions. Today, architecture reviews often require significant manual effort and depend on experienced architects who must interpret requirements, inspect design documentation, identify deviations, and explain potential risks. This master’s thesis will investigate how Generative AI can support architecture verification. The aim is to design and evaluate an AI-powered prototype that analyses architecture descriptions and diagrams against Ericsson Mandatory Architecture Requirements (MARs) and relevant design principles. The solution should identify potential violations, explain their security or architectural impact, provide traceable reasoning, and suggest practical improvements. The AI-generated results will be compared with assessments performed by experienced security architects to evaluate accuracy, consistency, explainability, and usefulness. What you will do:

• Review relevant literature and current approaches for AI-assisted architecture and security assessment.
• Study applicable Mandatory Architecture Requirements and design principles and translate them into verifiable evaluation criteria.
• Design and implement a prototype that uses Generative AI to analyse software or system architecture documentation.
• Identify potential non-compliance, explain the related security or architecture risk, and recommend improvements.
• Provide references to the requirements and design principles used in each assessment to support traceability and human review.
• Create representative architecture assessment scenarios and establish expert-reviewed reference results.
• Compare the AI assessments with those of experienced security architects using measures such as precision, recall, agreement, false-positive rate, explanation quality, and review effort.
• Analyse limitations, risks, and suitable human oversight for using Generative AI in architecture governance.

The skills you bring:

• Background in computer science, software engineering, cybersecurity, information technology, or a related field.
• Understanding of software or system architecture and security principles.
• Experience with Python and Large Language Models, prompt engineering, or Retrieval-Augmented Generation.
• Ability to work with structured and unstructured technical documentation.
• Interest in empirical evaluation, security architecture, and responsible AI.
• Strong analytical, problem-solving, and communication skills.

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: 791042