PhD Position in AI for Software Reuse and Agentic Development

How can AI agents build on existing software instead of reinventing it? Join this collaboration between TU Delft and ING to research more reliable agentic software development.

PhD Position in AI for Software Reuse and Agentic Development

Job description

Software intensive organizations rely on increasingly large and complex software ecosystems consisting of services, libraries, APIs, frameworks, documentation, and other shared engineering knowledge. Recent advances in generative AI and software engineering agents are changing how software is developed and how developers interact with these ecosystems. TU Delft is collaborating with ING to investigate how we can make enterprise software development more sustainable and reliable in this changing landscape.

We will develop new techniques and tools that help developers and AI agents make better use of existing software and developer knowledge. Our research will combine AI with software repository mining, program and architecture analysis, empirical software engineering, and studies with practitioners. The research will focus on real-world software engineering challenges at ING, while contributing scientific insights and open research results that can benefit the broader software engineering community.

Within this collaboration, we explore two main research directions:

Direction 1: Software Reuse in Enterprise Software Ecosystems

Large organizations invest substantially in reusable software assets. However, as a consequence similar functionality can be implemented independently across teams, increasing fragmentation and long-term maintenance costs. AI-assisted software development makes this challenge even more important: software engineering agents can rapidly generate new code, but may reproduce functionality that already exists elsewhere in an organization.

This direction investigates how software assets are discovered, consumed, adapted, and evolved across large software ecosystems. We will study where opportunities for reuse exist, how software can successfully be adapted across teams, how reusable assets evolve over time, and how developers and AI agents can be guided towards suitable existing software. Ultimately, we aim to develop intelligent techniques that help organizations maximize reuse while reducing unnecessary duplication and maintenance effort.

Direction 2: Reliable Agentic Software Development

AI software engineering agents can increasingly perform tasks such as implementing features, fixing bugs, testing, and refactoring software. Their success, however, depends not only on the underlying AI models, but also on the engineering context available to them. In enterprise environments, relevant knowledge is distributed across source code, documentation, architecture descriptions, requirements, APIs, development history, and organizational practices.

This direction investigates the engineering foundations required for reliable agentic software development. We will study what context agents need for different software engineering tasks, what makes specifications sufficiently complete and precise, how stale or incomplete context and software complexity affect agent performance, and how organizations can determine when tasks can be reliably delegated to AI agents. The goal is to develop techniques and safeguards that enable organizations to integrate increasingly autonomous software engineering agents while maintaining software quality and human oversight.

Job requirements

Required

• Master's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field
• Proficiency in the English language

Additional requirements:

• Research focus, characterized by curiosity, data fluency, and critical thinking
• Engineering mindset, including ability to create experimental prototypes and demonstrators
• Team player, good listener, and ready to help

To thrive as a PhD candidate, it’s crucial to have a strong research mindset driven by curiosity and passion for your topic. Reflecting on your motivation for pursuing a PhD trajectory is essential, as this path involves unique challenges and uncertainties inherent to scientific exploration. Success requires dedication, adaptability, the ability to analyze complex problems, manage your time effectively, innovate and stay resilient under pressure. Combined with the ability and willingness to work independently and collaborate well, these qualities are indispensable for a fulfilling PhD journey. These experiences will build you as an independent researcher, expand your professional network, and pave the way for diverse career paths, inside or outside academia.

TU Delft (Delft University of Technology)

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

Faculty of Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three scientific disciplines. Combined, they reinforce each other and are the driving force behind the technology we all use in our daily lives. Technology such as the electricity grid, which our faculty is helping to make completely sustainable and future-proof. At the same time, we are developing the chips and sensors of the future, whilst also setting the foundations for the software technologies to run on this new generation of equipment – which of course includes AI. Meanwhile we are pushing the limits of applied mathematics, for example mapping out disease processes using single cell data, and using mathematics to simulate gigantic ash plumes after a volcanic eruption. In other words: there is plenty of room at the faculty for ground-breaking research. We educate innovative engineers and have excellent labs and facilities that underline our strong international position. In total, more than 1000 employees and 4,000 students work and study in this innovative environment.

Conditions of employment

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1,5 year contract with an official go/no go progress assessment within 15 months. Followed by an additional contract for the remaining 2,5 years assuming everything goes well and performance requirements are met.

Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from €3204 - €4051 gross per month, from the first year to the fourth year based on a fulltime contract (38 hours), plus 8% holiday allowance and an end-of-year bonus of 8.3%.

As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.

The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.

• Hours per week: 36-40
• The PhD position will be fully at TU Delft, with strong collaboration with ING.
• Will you need to relocate to the Netherlands for this job? TU Delft is committed to make your move as smooth as possible!
• Coming to Delft Service organises events to help you settle in the Netherlands, and expand your (social) network in Delft.
• A Dual Career Programme is available, to support your accompanying partner with their job search in the Netherlands.

Additional information

As part of knowledge security, TU Delft conducts a risk assessment during the recruitment of personnel. The assessment is based on information provided by the candidates themselves, such as their motivation letter and CV, and takes place at the final stages of the selection process. When the outcome of the assessment is negative, the candidate will be informed.