Centre of Research in Myology, Sorbonne Université-Inserm, Institut de Myologie Groupe Hospitalier Pitié‐Salpêtrière, Paris, France.

Description:
Within the EU-Horizon Europe CoFund Project “ERDERA, European Rare Diseases Research Alliance”, a medical research assistant / engineer position specializing in Artificial Intelligence and Natural Language Processing (NLP) is available in the team of Gisèle Bonne.

The missions of the ERDERA are to transform rare disease research and care in Europe. By building on the achievements of previous partnerships’, ERDERA will: i) enhance collaboration, align research funding and enable optimal integration of EU and national rare diseases strategies and plans; ii) bridge the huge gap that hampers the translation of research results into cost-effective solutions that reach patients, and iii) help reduce the fragmentation of knowledge and data and evolve towards a holistic approach to research and innovation in rare diseases.

The selected candidate will specifically focus on leveraging AI technologies, including advanced NLP methodologies, named entity recognition, and retrieval augmented generation techniques to systematically produce high-quality datasets from published biomedical literature. These datasets will be essential for subsequent curation processes and integration into the Treatabolome database - an innovative platform capturing treatable genes and corresponding treatment strategies for Rare Diseases.

Responsibilities include:

• Developing and implementing NLP algorithms and models to efficiently mine, extract, and structure biomedical information from scientific literature.
• Utilizing named entity recognition (NER) techniques to accurately identify and classify biomedical entities relevant to rare disease research.
• Implementing retrieval augmented generation strategies to enhance the accuracy and comprehensiveness of generated datasets.
• Collaborating closely with expert clinicians to validate and curate the extracted data.
• Extending and optimizing the Treatabolome database through continuous integration of curated datasets.

The candidate will join a multidisciplinary team with robust expertise in molecular genetics of neuromuscular disorders, closely interacting with national and international reference centers.

The research environment is situated at a Joint Research Unit of Sorbonne Université and INSERM, within the Myology Institute on the Pitié‐Salpêtrière Hospital campus, providing access to state-of-the-art computational and research facilities in a dynamic international setting.

Qualifications:

• Master's degree or equivalent in Computational Biology, Bioinformatics, Computer Science, Medical Sciences, or a related field.
• Proven expertise and practical experience in AI and NLP applications, particularly in biomedical text mining, named entity recognition, and retrieval augmented generation.
• Familiarity with human genetics and bioinformatics tools. Prior experience or knowledge in neuromuscular disorders or myology would be advantageous but is not mandatory.
• Salary and Contract Information: Salary commensurate with Inserm Status guidelines, dependent upon experience.
• Initial contract duration: 2.5 years.

Application Instructions: Interested candidates are invited to submit their applications, which should include a detailed CV, a brief overview of previous relevant projects, and contact information for two professional references to: Gisèle Bonne, PhD and Antonio Atalaia, MD Center of Research in Myology Sorbonne Université - Inserm UMRS 974 Institut de Myologie G.H. Pitié-Salpêtrière 47, boulevard de l'Hôpital F-75 651 Paris Cedex 13 - France

Tel: +33 1 42 16 57 23 (or 17)

E‐mail : gisele.bonne@inserm.fr / antonio.marques-atalaia@inserm.fr

https://recherche-myologie.fr/

https://erdera.org

Date: The position is available from June 2025