Building Project Oracles for Hardware-Aware Software Development using Domain-Adaptive AI

What you will do

At imec, the System Software team builds applications that interact with complex hardware systems, from implantable neural probes to lens-free imaging platforms, DNA sequencers, and edge computing systems. Developing and maintaining this software requires deep knowledge of the underlying hardware: register maps, pin configurations, timing constraints, and countless other details scattered across datasheets, schematics, and specification documents.

The System Software team works with a rich body of technical knowledge spanning hardware documentation, design specifications, and implementation details. Unlocking this knowledge effectively is key to faster development and better engineering decisions. While AI-powered coding assistants such as GitHub Copilot can support code generation, they often need deeper project-specific context to be truly effective in our domain. In this internship, you will help bridge that gap by building "project oracles" that make project-specific knowledge more accessible and actionable throughout the development process.

During this internship, you will explore how large language models can be adapted to our domain, build a prototype that turns technical project documentation into a practical knowledge source, and evaluate its value for real engineering use cases.

You will also examine how this prototype can fit into developers’ workflows and contribute recommendations for applying these techniques effectively within the team.

By the end of the internship, you will deliver a working oracle for one project, a reproducible architecture that can be extended to other projects, and a set of findings and recommendations on the most effective techniques for our use case.

What we do for you

imec is a world-leading research and innovation hub in nanoelectronics and digital technologies. In the Innovative Systems and Software Applications (ISSA) department, you will collaborate with experts in software engineering who build the tools and applications that bring imec's hardware innovations to life. You will work in the System Software team within the Software Development & Prototyping (SDP) group, where you will be embedded in a team of experienced developers working on real-world systems across domains such as neuroscience, imaging, and genomics.

We offer a stimulating environment at the intersection of AI and embedded systems, hands-on experience with state-of-the-art LLM techniques, and the opportunity to build something that directly impacts how our engineers work every day.

Who you are

• You are a MSc student in Computer Science,  AI, or a related field
• You are available for a period of 3-6 months (share your available period in the application)
• You can communicate clearly and work independently
• You have good written and verbal English skills
• You enjoy coding in Python and are interested in writing clean, reusable code
• You are curious about AI, large language models, and how they can be applied to real-world engineering problems
• You are eager to learn, take initiative, and deliver tangible results
• Experience with RAG frameworks, LLM fine-tuning, or vector databases is a plus but not required
• Familiarity with embedded systems or hardware-adjacent software development is a bonus