Postdoctoral Position, AI for Retrosynthesis Reaction Prediction

About the role

We are seeking a highly motivated postdoctoral researcher to join an interdisciplinary team developing artificial intelligence solutions for retrosynthetic analysis and reaction prediction. The role bridges computational chemistry and machine learning to create sustainable synthetic routes for complex molecules in pharmaceuticals, agrochemicals, and related fields.

Key responsibilities

• Design and implement AI/ML models such as graph neural networks and transformer‑based architectures for retrosynthetic pathway prediction.
• Apply deep‑learning techniques to forecast reaction outcomes, optimize conditions, and discover novel synthetic routes.
• Curate, clean, and manage large reaction datasets from literature, patents, and proprietary sources.
• Integrate predictive tools with cheminformatics platforms and molecular modeling software.
• Collaborate with synthetic chemists to experimentally validate predictions and refine laboratory workflows.
• Publish research findings in high‑impact journals and present at conferences.
• Mentor graduate students and contribute to team capacity‑building activities.

Required profile

• Ph.D. in Chemistry, Computational Chemistry, Cheminformatics, Computer Science, or a related discipline.
• Demonstrated expertise in machine learning or deep learning applied to chemical reaction prediction or retrosynthesis.
• Strong problem‑solving abilities and experience working in multidisciplinary research environments.

Required skills

• Python programming.
• ML frameworks: TensorFlow, PyTorch, or JAX.
• Cheminformatics tools: RDKit, Open Babel.
• Familiarity with reaction databases such as Reaxys, USPTO, Pistachio.
• Experience with graph‑based learning, attention mechanisms, and transformer architectures for chemical data.
• Knowledge of computer‑aided synthesis planning tools (e.g., AiZynthFinder, ASKCOS, IBM RXN).
• Exposure to cloud computing and high‑performance computing resources.