imec logo
Contact
CMOS: advanced and beyond
Discover why imec is the premier R&D center for advanced logic & memory devices.
Integrated photonics
Take a look at technologies for optical transceivers, sensors and more.
Health technologies
See how imec brings the power of chip technology to the world of healthcare.
Sensing and actuation
Explore imec’s CMOS- and photonics-based sensing and actuation systems.
Connectivity technology
Look into our reliable, high-performance, low-power network technologies.
More expertises
Discover all our expertises.
Research
Be the first to reap the benefits of imec’s research by joining one of our programs or starting an exclusive bilateral collaboration.
Manufacturing
Go from idea to scalable and reliable semiconductor manufacturing with IC-Link.
Venturing
We create and co-create new ventures, and we invest in and accelerate existing ventures.
Education and workforce development
Imec supports formal and on-the-job training for a range of careers in semiconductors.
NanoIC pilot line
Aligned with the EU Chips Act, access to the pilot line will accelerate beyond-2nm innovation.
Semiconductor technology
Life sciences and health solutions
Data and telecommunication
Automotive technologies
Robotics technology for Industry 4.0
More applications
/Token-Efficient AI-Agent Design for an Operational Knowledge Hub

Token-Efficient AI-Agent Design for an Operational Knowledge Hub

Master internship, Bachelor internship - Leuven | Just now

Optimising token use while delivering accurate, reliable, and traceable operational answers.
Apply
This internship focuses on developing and evaluating a token-efficient AI-powered knowledge hub that provides a single point of access to operational information distributed across collaboration platforms, documentation repositories, and tutorials. In addition to curating approved knowledge sources and configuring a prototype agent, the intern will investigate how prompt design, context selection, retrieval strategies, knowledge summarisation, conversation-memory management, and response-length controls can minimise input and output token usage. These approaches will be evaluated against answer accuracy, relevance, source traceability, reliability for unsupported questions, latency, and computational cost. A three-month placement will deliver a tested prototype, an initial token-efficiency evaluation, and a handover package; an extension to six months will support broader experimentation, a user pilot, feedback-driven improvements, and recommendations for future deployment. The work will provide practical research experience in AI-agent development, information retrieval, knowledge management, systematic evaluation, and responsible use of organisational information.

Research topic: Token-efficient AI-agent design: investigate and evaluate methods for minimising input and output token usage while maintaining answer accuracy, relevance, source traceability, and reliable handling of unsupported questions. The work may compare prompt design, context selection, retrieval strategies, knowledge summarisation, conversation-memory management, and response-length controls, with the goal of identifying an effective balance between performance, latency, and computational cost.



Type of internship: Master internship, Bachelor internship

Duration: 3-6 months

Required educational background: Computer Science, Electrotechnics/Electrical Engineering, Other, IT

Supervising scientist(s): For further information or for application, please contact Saeideh Alinezhad Chamazcoti (Saeideh.AlinezhadChamazcoti@imec.be)

The reference code for this position is 2026-INT-298. Mention this reference code in your application.

Only for self-supporting students.


Applications should include the following information:

  • resume
  • motivation
  • current study

Incomplete applications will not be considered.
Apply
Who we are
Accept analytics-cookies to view this content.
imec's cleanroom
Accept analytics-cookies to view this content.

Related jobs

[NanoIC topic] AI-Driven semiconductor test data analytics

Your goal is to create a python based framework where an engineer can ask natural language questions on his electrical data and receive instant statistical insights and visual diagnostics.

Foundation Models, World Models and Continual Learning for Semiconductor Lithography and Metrology: Advancing Machine Learning towards High-NA EUV Process Control

Teaching machines to predict what will print

Design of a MEMS-based plasma sensor to measure ion energy and flux

The objective of this master thesis is to design a miniature MEMS sensor capable of monitoring ion energy and ion flux during semiconductor plasma processing.

Modelisation of light matter interaction for temporary bonding applications

As the semiconductor industry pivots from traditional node scaling toward system-level innovation, temporary bonding and debonding of wafers is a key steps for next industrial development. In this internship the goal is to explore the potential improvement of an advanced techniqu

Early-Stage Thermal Screening Methodology for Advanced HBM–GPU Integration

From early insight to informed system-level decisions

Runtime-Integrated Simulation of Accelerator Memory Behaviour for Distributed LLM Deployment

Where hardware meets software: integrate hardware simulation where it matters.
Job opportunities

Send this job to your email