JetBrains Research
Research is crucial for progress and innovation, which is why at JetBrains we are passionate about both scientific and market research
Meet Our Newest Innovators: Welcoming AI4SE Interns as JetBrains Employees!
Picture this: You’re working on your MSc thesis as an intern in software engineering, not just as an academic exercise, but side-by-side with an industry team, tackling real projects and real problems, refining code, and witnessing your ideas come alive. By the time you’ve graduated, you’re already a valued team member, ready to hit the ground running .
In a short series of posts, we will tell you about four recent graduates who have done exactly that, thanks to our AI for Software Engineering ( AI4SE ) research partnership with Delft University of Technology ( TU Delft ). Having recently completed their MSc thesis work as interns here at JetBrains, they are now starting full-time positions with us.
This first post will tell you a little about them and their experiences at JetBrains so far, and the second will go deeper into their new roles.
Incoming AI4SE graduates to JetBrains
While working on their MSc theses, these students got hands-on experience in the tech world. And now they’re full-time innovators sharing how their internships became the launchpad for their careers. Here are Milan, Nadine, Saga, and Sergey:
Milan de Koning, Nadine Kuo, Saga Rut Sunnevudóttir, and Sergey Datskiv
During their time as interns with us, they worked on projects covering various topics and contributed important research. For many of them, their work will grow into journal papers in the coming months.
Our AI4SE Partnership
The AI4SE program merges academic research with industry collaboration. Together with our partners at TU Delft, we are committed to advancing cutting-edge research on the impact and utilization of AI methodologies in software engineering, focusing on areas such as software development, testing, and programming education.
AI4SE was launched in 2023, and each year four to five students work together with researchers on topics within the five research tracks (more details on who is involved can be found on the AI4SE People page). Several of our teams participate: Software Testing Research, HAX, Dynamic Program Analysis, Education Research teams; alongside teams from the TU Delft side: AISE and CISE research labs from the Software Engineering Research Group and the Center of Education and Learning . The program additionally is part of the Innovation Center for Artificial Intelligence (ICAI).
What it’s like to be an AI4SE intern at JetBrains
Overall, the interns enjoyed the same status as full-fledged employees, with the encouragement to ask questions and present their own ideas. The environment is intellectually stimulating and the company culture is very supportive.
AI4SE students’ research topics
This cohort researched topics from different AI4SE tracks and worked with various JetBrains departments.
“The opportunity to work with cutting-edge technology is something that I am very grateful for.”
Here are more details on their thesis work:
Milan’s thesis looked at data leakage, or when a model sees parts of the test data during training. For the thesis, he:
- Worked within Track 1 and with the Software Testing Research team.
- Used metamorphic testing, which changes code without altering its meaning, to reveal when models rely on memorization rather than true understanding.
- Studied how this can lead to inflated results in automated bug-fixing systems.
Nadine’s thesis involved designing and evaluating a proactive AI assistant in enterprise integrated development environments (IDEs), to supplement earlier related work confined to controlled laboratory settings. For the thesis, she:
- Worked within Track 3 and with our Human-AI eXperience (HAX) and Fleet teams.
- Developed a system that proactively suggests code improvements via in-editor cues and the AI Chat, based on heuristics for help-seeking moments.
- Evaluated the final design with an in-the-wild study, engaging professional developers to understand how timing, representation, and context influence user experience and perceptions.
Saga’s thesis focused on evaluating the current status of state-of-the-art test generation tools for JavaScript and TypeScript. For the thesis, she:
- Worked within Track 1 and with the Software Testing Research and WebStorm teams.
- Built a benchmark for assessing these tools, specifically JetBrains AI Assistant.
Sergey’s thesis concerned improving the current state-of-the-art unit test-case generation approach with LLMs. For the thesis, he:
- Worked within Track 1 and with the Software Testing Research team.
- Studied the possible challenges and benefits of using LLMs for test case generation and integration into existing tools.
Tips for incoming students
“ It was inspiring to connect with like-minded peers who were also passionate about the future of AI in software engineering.”
Starting an internship at a new company might be daunting. Here, our graduates share some tips for future interns on how to get the most out of their experience:
From what we’ve seen so far, it’s clear that our graduates’ willingness to learn, ask questions, and jump right into challenging projects has created a rich experience both for them and for us. We look forward to sharing more about their experiences as they continue to grow with us. Stay tuned for Part II!
If you are a TU Delft student interested in joining AI4SE, contact Mitchell Olsthoorn for general questions about the thesis procedures, or reach out to the university track leads to learn about project opportunities.
Subscribe to JetBrains Research blog updates
