Job
In this role, you will develop high-quality datasets for AI applications, carry out automated document processing, and evaluate methods for Retrieval-Augmented Generation and Question Answering.
This listing has been machine translated. Show original
Job technologies
Your role in the team
- As part of the project, you will develop a high-quality, openly reusable dataset for AI applications in RDM and OS.
- The focus is on the automated processing and quality assurance of documents, as well as the development and evaluation of AI-ready datasets for Retrieval-Augmented Generation (RAG) and Question Answering (QA).
- Conceptualization and technical implementation of the FAIR Corpus, including the selection of suitable data sources, the development of data and metadata models, and the implementation of FAIR and CARE principles, taking legal, data protection, and ethical requirements into account.
- Development of automated processes for the acquisition, processing, cleansing, and quality assurance of documents and metadata.
- Creation of a RAG subcorpus, including the development and testing of suitable segmentation and retrieval methods.
- Development of a QA subcorpus using LLM-assisted generation and quality assurance of question-answer pairs.
- Development and execution of benchmarks to evaluate retrieval and QA quality.
- Documentation and provision of reproducible data processing and evaluation procedures, as well as presentation of project results.
Our expectations of you
Education
- Completed university degree (Master’s or equivalent) in Computer Science, Data Science, Computational Linguistics, or a related field.
Qualifications
- Knowledge of Natural Language Processing (NLP) and experience working with Large Language Models (LLMs).
- Interest in the development and evaluation of AI-based methods, as well as in research data management and Open Science.
- Independent, structured, and team-oriented approach to work.
- Very good German and English skills.
- Experience in developing automated data pipelines, data validation, and quality assurance is desirable.
- Knowledge of research data management, Open Science, and the FAIR and CARE principles is desirable.
Experience
- Good programming skills in Python and experience processing text and metadata.
- Experience with Retrieval-Augmented Generation (RAG), information retrieval, or question answering (QA) is desirable.
- Experience with LLM-assisted data generation, prompt engineering, or the evaluation of AI systems is desirable.
- Experience with Git, reproducible workflows, and software development is desirable.
- Experience in scientific communication and presenting research findings is desirable.
What we offer
- A challenging and varied role in a university environment, working with national and international partners.
- A workplace in a prestigious Baroque palace in the heart of the university campus; centrally located, with direct access to public transport and just 5 minutes from the main train station.
- A flexible working hours model, the option to work remotely (up to 50%), and 30 days of annual leave.
- Option to purchase the Deutschlandticket Job at a subsidized rate.
- An annual salary in accordance with TV-L pay grade E13, along with the standard social benefits and perks of public service, such as an occupational pension scheme (VBL).
Benefits
Work-Life-Integration
Higher take-home pay
Topics you will work on
Job locations
About your employer
Die Universität Mannheim ist eine Universität im baden-württembergischen Mannheim und zählt – 1907 als städtische Handelshochschule gegründet und 1967 in Universität umbenannt – zu den jüngeren Universitäten Deutschlands.
- Established Company
- Onsite, Hybrid
- Healthcare, Social Sector · Education System
More jobs
These jobs might also interest you
The role As a Forward Deployed AI Engineer, you go directly into our specialist departments, understand the processes, and develop production-ready AI and automation solutions that will fundamentally change the way the entire GGW Group operates. You do...
Hello, let's say WE! We - the HUK-COBURG Insurance Group - are among the top 10 in Germany. Founded over 90 years ago, we are now the leading insurer for private households with over 13 million customers and the largest German auto insurer. Our...
Operation, monitoring, and further development of the network infrastructure. Administration and configuration of firewalls, routers, and switches. Ensuring network availability, performance, and security. Participation in IT security concepts and...
