Worker Type:
Interns (Fixed Term) (Trainee)Posting Start Date:
July 16, 2026Job Description:
Project Title Extracting Knowledge from Documents: Enabling Semantic Search for technical documents
DESCRIPTION OF INTERN ASSIGNMENT
The conventional text documents have made it possible to efficiently retrieve large amounts of text data with the development of various search engines. However, these traditional search approaches frequently have lower accuracy in retrieval, particularly when documents have certain characteristics that call for more in-depth semantic extraction.
Internship Assignment
Internship project will focus on developing a workflow to enable document ingestion, metadata extraction and semantic search functionality for the library of technical reports. The intern will develop the workflow using suitable OpenSource Libraries and adapt them for the technical documents we are interested in. Metadata extraction will focus on identifying and extracting important information or features of a document, such as the author, title, subject classification, subject headings, and keywords. It will also involve extraction of structured data about the document, which can be used for various purposes like searching, cross-referencing, and categorizing the document.
Deliverables
- Workflow/pipeline code for metadata extraction and semantic search
- Internship report, Shell Report, Final presentation
-
DISCLAIMER:
Please note: We occasionally amend or withdraw Shell jobs and reserve the right to do so at any time, including prior to the advertised closing date. Before applying, you are advised to read our data protection policy. This policy describes the processing that may be associated with your personal data and informs you that your personal data may be transferred to Shell/Shell Group companies around the world. The Shell Group and its approved recruitment consultants will never ask you for a fee to process or consider your application for a career with Shell. Anyone who demands such a fee is not an authorised Shell representative and you are strongly advised to refuse any such demand. Shell is an Equal Opportunity Employer.Skills Required
- Develop workflow/pipeline for document ingestion and semantic search
- Use and adapt open-source libraries for document processing and semantic search
- Extract metadata such as author, title, subject classification, headings, and keywords
- Produce pipeline code and deliverables including internship report, Shell report, and final presentation
- Work with technical reports and adapt solutions to domain-specific document characteristics
What We Do
Shell is a global energy company with around 87,000 employees in more than 70 countries. We work together to power progress through more and cleaner energy solutions. We serve more than 30 million customers at almost 46,000 retail service stations every day. Our strategy is to accelerate the transition of our business to net-zero emissions, purposefully and profitably. #PoweringProgress
