Thesis: Cloud agent-based software development workflows

Cloud-based AI agents can support software development from an initial feature request through implementation and review, but developers still need to oversee requirements, quality, and design decisions. This thesis explores a reusable agent-driven development workflow with human checkpoints for inspecting progress, correcting decisions, and approving further work.

The assignment

• Design and build a cloud-based workflow that coordinates multiple agents to turn a feature ticket into a reviewed software implementation.
• Cover requirements refinement, implementation planning, changes to an existing codebase, test creation and execution, and review.
• Introduce checkpoints where a developer can assess, approve, or reject agent decisions and proposed actions.
• Create structured reports explaining changes and their rationale, helping developers oversee concurrent implementations with less context-switching effort.
• Make the prototype straightforward to adopt in both established and new projects.
• Test the prototype in practice and assess usability, integration, reuse across projects, and the effectiveness of human oversight.

Who we are looking for

• Studying towards a bachelor's or master's degree in computer science, computer engineering, or a related discipline.
• Expecting to graduate in June 2027.
• Fluent in both Swedish and English, in speech and writing.

Practical details

Based at Knightec Group's Sundsvall office. Start in January or March 2027. Apply through the company's careers page as soon as possible, no later than 30 November 2026. Questions can be sent to johanna.edstrom@knightec.se.