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

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