Development of a IT system integrated into an enterprise computer application for semantic analysis within industrial projects

Department

Engineering Department "Enzo Ferrari"

Main research activities/topics/projects

This opportunity aims at the development, implementation and field testing (at some companies in Emilia-Romagna Region) of an integrated messaging system within a well-established web app dedicated to order management in industrial environments.

The project will consist of two phases:

• in a first phase, the messaging system (“WhatsApp-like”) will have to be developed (both Backend and Frontend) with which users of the application will be able to exchange text messages and files. The messaging system will have to be integrated into an existing web app dedicated to project management. The messaging system will be tested in a couple of companies by about 100 users.
• In the second phase, the development of the backend part for advanced processing of the collected texts, through the integration of Large Language Models (LLM), will be carried out in order to enable accurate semantic analysis of project status.

This will require the implementation of preprocessing algorithms, NLP analysis, and integration of Large Language Models within the existing web app architecture. It will be necessary to design a scalable and efficient system that can handle large volumes of messages and ensure optimal performance in terms of processing speed and accuracy of semantic analysis.

Working language

Italian and English

Special entry requirements

- Solid knowledge of the Python language, with expertise in Natural Language Processing (NLP) and Machine Learning (ML). Good knowledge of the Python programming language.
- Experience in using the following Natural Language Processing (NLP) processing libraries:

• NLTK (Natural Language Toolkit)
• spaCy
• Transformers (for the integration of Large Language Models such as BERT, GPT, etc.

- Expertise in the design and implementation of RESTful backend services, understanding of the fundamentals of microservice architecture, and ability to develop efficient APIs.
 - Knowledge of text preprocessing algorithms, tokenization, syntactic analysis, semantic analysis, and other NLP techniques for text processing and interpretation.
- Familiarity with machine learning concepts, understanding of supervised and unsupervised machine learning models used in natural language processing.
- Proficiency in using machine learning frameworks or libraries for training custom models in NLP, such as TensorFlow or PyTorch.
- Knowledge of agile software development methodologies and familiarity with version control tools such as Git.
- Good understanding of database concepts and ability to work with complex data structures.

Duration in months (min-max)

PhD sandwich: 4-12

Post Doc: 4-12