Orano Med is a biotechnology company owned by Orano. Our ambition is to develop a new generation of targeted cancer therapies using the unique properties of lead-212, a rare alpha-emitting radioisotope with highly promising medical properties.
Responsabilities :
In collaboration with the Discovery team, build and apply cheminformatics and computational chemistry capabilities to support the Design–Make–Test–Analyze (DMTA) discovery cycle in radiotheranostics.
Contribute to the advancement of the radiotheranostic pipeline by applying computational approaches such as molecular docking, ligand-based design, diversity and conformational analyses, together with machine learning and AI methods, to support multiparameter optimization of radioligand candidates.
Develop, optimize, and implement computational tools, workflows, and methods (e.g., docking, molecular dynamics, free-energy calculations, ML/AI-assisted design) to strengthen internal discovery capabilities and accelerate project progression.
Provide computational support and scientific input across key discovery stages, including target assessment, hit identification, and lead optimization, working closely with medicinal chemistry and biology teams.
Collaborate with the IT and data science teams to help integrate AI-enabled tools into day-to-day drug design workflows.
Clearly communicate computational results, design hypotheses, and data-driven recommendations to multidisciplinary project teams.
For the time being, the position will be based in Chatillon, but in March the site is scheduled to move to Villejuif.
Ph.D. in Computational Chemistry, Theoretical Chemistry, Chemistry, or a related field, with industry and/or postdoctoral experience applying computational methods in drug discovery or radiopharmaceutical developme.
Strong expertise in computational chemistry methods relevant to radiotheranostics—including molecular docking, virtual screening, molecular dynamics, FEP, homology modeling, QM, and pharmacophore modeling—and proficiency with open-source (e.g., OpenMM) and/or commercial platforms (e.g., Schrödinger, OpenEye, MOE) in an industry setting.
Experience modeling peptides and small molecules, with solid knowledge of structure–activity relationships and multiparameter optimization for radioligand design (affinity, stability, clearance, selectivity).
Hands-on experience applying AI/ML approaches to molecular design and decision-making, including QSAR, property prediction, compound prioritization, diversity selection, and data-driven workflows integrated with physics-based methods.
Proficiency in Python for data analysis, workflow automation, pipeline development, and deployment on HPC or cloud environments, including integration of AI/ML models into discovery workflows.
Ability to collaborate in a multidisciplinary environment, translating computational and AI-driven insights into actionable design hypotheses with chemistry, biology, and radiochemistry teams.
Châtillon, Île-de-France, France