About this role
Summary: Develops automated computational workflows and trains AI models to analyze DNA-encoded library screening data. Screens ultra-large chemical libraries to identify novel entry points for drug discovery.
We are an international and independent pharmaceutical group with a human scale, governed by a Foundation. Our unique model is our pride but, above all, it enables us to fully serve our vocation: “Committed to therapeutic progress for the benefit of patients”.
A global leader in cardiology today, we have chosen to become a focused and innovative player in oncology by 2030, by targeting hard-to-treat cancers and dedicating more than 70% of our R&D budget to them. This is a challenge we are pursuing alongside the development of our generic business to ensure access to quality healthcare for all, at a lower cost.
Who are we? 22,000 passionate employees of more than 50 nationalities, driven by an entrepreneurial spirit. Every day, we move forward with and for patients, with and for our teams, driven by the desire to care, to dare, to develop, and to commit ourselves to being useful to those who need it.
Come and experience our commitment, and help us bring it to life #MovedByYou
[www.servier.com](http://www.servier.com/)
We are seeking a Postdoctoral Researcher to drive innovation in hit discovery by leveraging modern lead-finding approaches and artificial intelligence. The mission is to discover new chemical matter by developing automated workflows for DNA-encoded library (DEL) analysis, training advanced AI models, and virtually screening ultra-large chemical libraries to identify novel entry points for drug discovery programs.
#### Main Responsibilities
- Workflow Development: Produce and implement robust, automated computational workflows for the comprehensive analysis of DNA-encoded library screening data.
- Database Management: Manage the formatting, structuring, and organization of the DEL screening database, ensuring data quality and readiness for AI exploitation.
- AI Model Training: Design, train, and optimize machine learning and deep learning models utilizing complex DEL datasets to predict molecular properties and activity.
- Ultra-Large Library Screening: Deploy trained AI models to virtually screen ultra-large chemical libraries of billions of compounds to identify novel chemical entry points.
- Cheminformatic Analysis: Perform large-scale screening data analysis to build SAR models and guide hit-to-lead processes.
- Data Stewardship: Manage the curation of DEL screening results to foster FAIR data principles.
- Cross-Functional Collaboration: Partner with interdisciplinary teams across R&D to advance computational tools for hit discovery.
#### Required Skills and Experience
- - Educational Background: PhD degree in Chemoinformatics, Computational Chemistry, Data Science, Bioinformatics, or a closely related computational discipline.
- Programming: Advanced proficiency in Python.
- Cheminformatics: Expertise in toolkits such as RDKit and DNA-encoded library (DEL) informatics.
- Artificial Intelligence: Applied experience in Machine Learning and Deep Learning frameworks.
- Cloud and Tools: Strong expertise in GitHub and experience with Google Cloud Platform (GCP).
- Soft Skills: Scientific acumen, boldness, creativity, and the ability to work effectively in project mode within interdisciplinary teams.
- Communication: Excellent written and oral communication skills in English.
We are committed to equal opportunity and the development of talent in all its diversity. We value experience as much as the desire to commit daily to being useful to therapeutic progress for the benefit of patients. If you recognize yourself in this offer and these few lines, take this opportunity to meet us.