/Student project: Building an AI Agent for PFAS-Related Research Topics

Student project: Building an AI Agent for PFAS-Related Research Topics

Research & development - Wageningen | Just now

Student project: Building an AI Agent for PFAS-Related Research Topics

*Important for non-EU students: You'll need to be registered at a Dutch university to meet immigration requirements.

Build a high-fidelity, low-power RAG based AI model to inform and educate users on per polyfluoroalkyl substances (PFAS) legislative topics.

What you will do

As researchers, it can be difficult to keep track of topics that are adjacent to our research and even directly impact our research opportunities and direction. PFAS is a rapidly evolving and highly interdisciplinary topic, strongly shaped by ongoing legislative and regulatory developments across regions and sectors. Building an AI agent to support researchers in this space offers the opportunity to systematically collect, structure, and interpret complex and fragmented regulatory information, enabling more efficient tracking of policy changes and their implications. Such a tool can assist in navigating evolving legislative landscapes, supporting informed decision-making and aligning research and innovation with current and future regulatory requirements.

In this internship, you will focus on updating, enhancing and maturing the existing AI agent as well as automating the process of updating the agent’s database. This may include, but is not limited to:

  • Conducting a comprehensive literature review on the subject.
  • Extending the current functionalities of the interface to support new use cases or data types.
  • Curating additional data sources and integrating it into the existing knowledge base through semi-automatic updates with a human-in-the-loop.
  • Implement strict model constraints to ensure high fidelity output.
  • Improving robustness, scalability, or user experience of the interface.
  • Iteratively testing and evaluating enhancements in collaboration with supervisors and/or test users.
  • Working in an agile environment to deliver timely, effective results.
  • Optimizing the model for low power consumption.

The internship work and activities will be organized with a scrum-like methodology: you will maintain the backlog in coordination with your supervisors. You will select prioritized tasks from the backlog, and you will tackle and evaluate them on a weekly basis. At the end of each weekly iteration, you will showcase the progress made and will reflect on insights and improvements to focus on. Additional stakeholders may take part in the showcases to get better feedback on the study.

What we do for you

You will do your internship at imec within OnePlanet Research Center. OnePlanet is a multidisciplinary collaboration between Wageningen University & Research (WUR), Radboud University, Radboud UMC and nano-technology world-player imec. Your work here will not only be of academic relevance but also translated into practical applications where possible.
 
During this internship you will:

  • Have access to a diverse team of experts with the necessary technical and domain expertise to supervise and support you.
  • Be working on a relevant, real-world problem where you have freedom to come up with creative ideas to solve the various technical challenges.
  • Join the Domain AI team of OnePlanet, which employs state-of-the-art knowledge on AI agents and sustainability of the industry.
  • Be able to exchange views and knowledge with the OnePlanet and imec community of experts and scientists, widening your professional network.

At OnePlanet we embrace diversity and thus give equal opportunities to intern candidates with diverse backgrounds.  

Who you are

  • You are a MSc student in AI, Data Science, Informatics, and/or Engineering equivalent.
  • You have an affinity for AI research and sustainability topics.
  • You are organized and communicative.
  • You can work independently and manage multiple tasks.
  • You have a basic understanding of Agile/Scrum.
  • You have experience with Python and Azure or similar.
  • Familiarity with AI techniques (RAG and/or LLMs) are a bonus
  • You are entitled to do an internship in the Netherlands. This means that you are either an EU/EEA citizen, or a non-EU/EEA citizen who is studying at a Dutch university and needs to do an internship as part of your studies.

Interested

Does this position sound like an interesting next step in your career at imec? Don’t hesitate to submit your application by clicking on ‘APPLY’.
Should you have more questions about the job, you can contact jobs@imec.nl.

Who we are
Accept analytics-cookies to view this content.
imec's cleanroom
Accept analytics-cookies to view this content.

Send this job to your email