Master's thesis: Does continuous use of AI-assisted development make subsequent AI-assisted development more costly or difficult?
Technology, Data & Digital · Data, AI & Analytics · Machine Learning · Software Engineering · Data Science
In short
This master's thesis at RISE Computer Science in Kista investigates the long-term impact of AI-assisted development on software engineering. The project will analyze how the continuous use of AI tools like Large Language Models affects the cost and difficulty of future AI-assisted development by comparing original and AI-generated codebases.
Responsibilities
- Investigate how the structure and development history of a software project affect the ability of LLMs to implement new features.
- Select suitable open-source projects.
- Recreate projects using AI-based development tools, simulating projects built with extensive AI assistance.
- Implement new features with clearly defined completion criteria using AI on both original and AI-generated codebases.
- Evaluate the process based on development time, token consumption, number of attempts, and successful completion.
Requirements
- Currently enrolled in a master's program.
- Solid knowledge of machine learning theory.
- Good programming skills, especially in Python.
- Interest in computer systems and solving complex problems.
Desired Qualifications
- Experience with AI-based development tools.
- Familiarity with Internet of Things (IoT) and Edge computing.
- Experience working with open-source projects.
Benefits
- Opportunity to conduct a master's thesis.
- Partially remote work option.
#AI#Software Development#LLM#Machine Learning#Python#Computer Networks#IoT#Edge Computing#KTH#Research
Company
RISE Research Institutes of Sweden
Job Posted
3 days ago
Expires
in 3 weeks
Employment Type
Internship
WorkMode
Hybrid
Experience Level
Entry
Locations
Kista, Sweden
Qualification
Master
Applicants
Be an early applicant