Lead Scientist in Computational Drug Discovery, executing structure-guided design and computational analyses to support drug discovery projects from early hits through lead selection.
Locations (2)
Copenhagen, Capital Region, Denmark
Boston, Massachusetts, United States
Responsibilities
Co-develop discovery hypotheses and molecular design strategies together with experimental colleagues
Provide structure-guided analysis and actively participate in drug discovery projects, from early hits to lead selection
Generate de novo hits and optimize existing hits with computational methods
Develop and maintain computational workflows within the computational drug discovery pipeline
Develop and maintain computational tools for the Discovery Research organization
Requirements
PhD in Computational Chemistry
PhD in Bioinformatics
PhD in Computational Biology
Nice to have: AI-based peptide and protein structure prediction and design methodologies
Nice to have: Machine learning predictive models for drug property prediction
Execute structure-guided design and computational analyses with a focus on immediate deliverables and operational objectives, using advanced analytical and technical skills to support drug discovery projects from early hits through lead selection.
Locations (2)
Copenhagen, Capital Region, Denmark
Boston, Massachusetts, United States
Responsibilities
Co-develop discovery hypotheses and molecular design strategies together with experimental colleagues
Provide structure-guided analysis and actively participate in drug discovery projects, from early hits to lead selection
Generate de novo hits and optimize existing hits with computational methods
Develop and maintain computational workflows within the computational drug discovery pipeline
Develop and maintain computational tools for the Discovery Research organization
Requirements
PhD in Computational Chemistry
PhD in Bioinformatics
PhD in Computational Biology
Internship in Computational Biophysics for Protein Property Prediction
Investigate whether information from molecular simulations can help predict protein properties such as stability and aggregation, using in-house experimental data.
Responsibilities
Set up, run and analyze Molecular Dynamics and Monte Carlo simulations of proteins, mainly antibodies and nanobodies.
Calculate descriptors from the simulations (e.g. flexibility, conformational ensemble characterization, surface properties) and relate them to experimental data.
Build a predictive workflow that combines simulation-derived descriptors with statistical or machine learning models.
Benchmark publicly available prediction tools, including generative AI for structural ensemble prediction, against Sanofi in-house data.
Present results to computational and experimental colleagues and document the workflow.
Requirements
Master’s program in biophysics, computational chemistry, structural biology, bioinformatics, physics or a related field
Nice to have: Protein structure knowledge (antibodies or nanobodies)
Nice to have: AI or machine learning (scikit-learn, PyTorch, protein language models, structure prediction tools)