Would you like to work in an innovative and supportive environment at
the forefront of AI developments?! The objective of this 6 month
internship working for the Lingua Custodia Lab (Research and
Development team) is to study LLM fine-tuning in the context of
financial conversational data (or instructions). You will be working on
supervised instruction fine-tuning and reinforcement learning from
human feedback. Theoretical and practical knowledge in all of these
mentioned topics are essential to carry out the internship.


Internship organisation

-   Internship supervised by the Lingua Custodia Lab (R&D team)
-   Internship of 6 months in Paris (fully on-site)
-   Full time, 35 hours weekly.
-   Ticket restaurant and 50% reimbursement of navigo pass
-   Starting date: Early 2024


Internship objectives

-   Study state-of-the art in Large Language Models (LLMs) fine-tuning.
-   Compare different models through systematic experiments.
-   Collect large amounts of conversational data (from public sources)
-   Fine-tune LLMs on conversational chat


Required qualifications and experience

-   Master's Degree student in Computer Science, Machine Learning or
    Natural Language Processing.


Required qualifications and experience

-   Experience with LLMs (class or personal projects) (this is a must)
-   Experience with Huggingface library (this is a must)
-   Proficient in English and/or French.


To apply:

Please send your CV to :
Raheel Qader - raheel.qader@linguacustodia.com