Trainee for the indexing of scientific documents with the aid of large language models (LLMs)

Swiss Light Source; Villigen; Vor Ort; CHF 80’000 - 100’000; Vollzeit

Zusammenfassung

An established research institute is seeking a Trainee to assist in indexing scientific documents using cutting-edge large language models. This internship offers the chance to work on innovative projects that address significant challenges in science and technology. As part of an international team, you will engage in tasks such as interpreting scientific publications, managing data in a vector database, and developing user interfaces for LLM interactions. This is a unique opportunity to gain hands-on experience in a dynamic research environment, contributing to sustainable solutions for society while advancing your academic career.

Leistungen

Interdisciplinary Collaboration

Dynamic Work Environment

Qualifikationen

• Student in computer science or similar, at least in penultimate year.
• Experience with running or accessing large language models.

Aufgaben

• Support interpretation of scientific documents using LLMs.
• Assess indexing possibilities for images and tables.

Kenntnisse

Large Language Models (LLMs)

Interpreting Scientific Publications

Database Management

User Interface Development

Ausbildung

Bachelor in Computer Science or similar

Tools

Vector Database

API for Cloud-based LLM

Jobbeschreibung

You Are Here

• PSI Home
• Career & Education
• Job Opportunities

The Paul Scherrer Institute PSI is the largest research institute for natural and engineering sciences within Switzerland. We perform cutting-edge research in the fields of future technologies, energy and climate, health innovation and fundamentals of nature. By performing fundamental and applied research, we work on sustainable solutions for major challenges facing society, science and economy. PSI is committed to the training of future generations. Therefore, about one quarter of our staff are post-docs, post-graduates or apprentices. Altogether, PSI employs 2200 people.

For the Large Research Facilities Division we are looking for a Trainee for the indexing of scientific documents with the aid of large language models (LLMs).

Position Details:
Internship
Index No: 8123-T1
100%
Contract Duration: 3 months

Your tasks:

We are using retrieval augmented generation (RAG) to support a large language model (LLM) answering questions related to our accelerators. Source documents include scientific publications, as well as internal documents. Many of these documents include images, tables, and equations, which are not directly accessible to be indexed in a language-based embedding.

You Will Help Address These Issues By:

• Support the interpretation of scientific publications and internal notes by large language models
• Assess possibilities to index images, tables, and equations
• Store embeddings in a vector database
• Use a large language model to search this database, and answer user questions
• Build a user interface for this model

The vector database and the large language model run locally on hardware located at PSI.

Your profile:

• You are a student in computer science or similar, and you are at least in your penultimate year of undergraduate study (minimum 4 semesters)
• You have experience running a large language model locally, or you use an API to access a cloud-based LLM
• You are an open-minded person who enjoys working in an international team
• You have not yet completed your Master’s thesis

We offer:
Our institution is based on an interdisciplinary, innovative and dynamic collaboration.

For further information, please contact Dr Rasmus Ischebeck, phone [phone] or email [e-mail].

Please submit your application online for the position as a Trainee (index no. 8123-T1).

Paul Scherrer Institut, Human Resources Management, Ladina Goerre, 5232 Villigen PSI, Switzerland.