EXPLORE YOUR NEXT CHAPTER
Thesis Worker - Accelerating Software Development with AI: Productivity and Quality in TRATON One OS
Scania
Source: Headcount Labs · original listing ↗
Job data: Headcount Labs, ODbL 1.0. Job descriptions belong to their employers.
Posted yesterday
About this role
30 hp - Accelerating Software Development with AI: Productivity and Quality in TRATON One OS Introduction Are you interested in exploring how Artificial Intelligence can transform the way software is developed for next-generation vehicles? We are looking for two Master's students to jointly investigate how AI-assisted development can accelerate software engineering while maintaining high standards of quality. The project will be carried out within TRATON R&D, working with engineers developing TRATON One OS (TOOS), the software platform for future generations of TRATON vehicles. Background As vehicles become increasingly software-defined, efficient development and reliable software quality are more important than ever. TRATON One OS is a key part of this transformation, providing a common software platform across the TRATON Group. Recent advances in generative AI and Large Language Models (LLMs) offer exciting opportunities to support software development, from translating functional requirements into executable code to generating and evaluating automated tests. However, generating code faster does not necessarily mean delivering working software faster. AI-generated solutions still require verification, integration, review and potentially significant rework. This thesis explores how AI can be applied across the development workflow and, importantly, how its actual benefits can be measured. Objective The objective is to investigate whether AI-assisted development can reduce the total engineering effort required to implement and test software functions within TOOS, while meeting the same predefined software quality criteria as conventional development. The central research question is: How much can AI assistance accelerate the development of software functions, from functional description to tested implementation, without compromising software quality? The study will evaluate both productivity and quality, including development time, testing effectiveness, defects, and the effort required for human review and corrections. Job description The two students will jointly design, implement and evaluate an AI-assisted software development workflow using representative functions from the TOOS environment. The work will include: • Investigating existing development practices and relevant AI-assisted software engineering techniques. • Selecting and modeling a limited set of representative software functions, including requirements and acceptance criteria. • Developing a prototype workflow using approved AI tools to support implementation, test generation and review. • Comparing conventional and AI-assisted development approaches using equivalent requirements and quality criteria. • Evaluating total engineering effort, software correctness, requirements coverage, test effectiveness and necessary human intervention. • Investigating how the approaches handle a realistic change in functional requirements. • Presenting conclusions and recommendations for the potential use of AI-assisted development within TOOS. The project is designed for two students with complementary areas of focus: Student 1 – AI-assisted function development : Function modeling, structured prompting, AI-supported code generation and implementation. Student 2 – AI-assisted testing and quality evaluation : Test generation, independent verification, software quality measurements and evaluation methodology. Both students will collaborate on the experimental design, development activities, analysis and final thesis report. The expected outcome is a working prototype, an evidence-based comparison of development approaches and practical recommendations on where AI can improve software engineering efficiency without sacrificing quality. Education/program/focus We are looking for students pursuing a Master's degree in Computer Science, Software Engineering, Artificial Intelligence, Machine Learning or a closely related field. A strong interest in software development and practical applications of AI is essential. Experience or knowledge in one or more of the following areas is advantageous: • Generative AI, LLMs and prompt engineering. • Software development and programming. • Automated software testing and continuous integration. • Requirements engineering or model-based development. • Experimental evaluation and data analysis. We value curiosity, analytical thinking and an interest in applying emerging technologies to real-world engineering challenges. Number of students : 2 students working jointly on one thesis project. Start date for the thesis work : To be agreed, preferably spring 2027. Estimated time required : 20 weeks full-time, corresponding to 30 ECTS per student. Location : TRATON R&D, Södertälje, Sweden. Contact persons and supervisors Industrial supervisor: To be confirmed. Contact person: Thomas Edwall, Unit Manager CHIPPS Operating System | TGRECHV Domain Cloud & Embedded Platform | EE Platform | TRATON Group R&D Academic supervisor and examiner: Appointed by the students' university. Application: Your application must include a CV, personal letter and transcript of grades A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.