Postdoctoral Chemical Data Scientist

We are seeking a highly motivated and skilled Postdoctoral Fellow in Chemical Data Science to join a new Innosuisse-funded collaborative research project that seeks to create an intelligent automated synthesis platform, incorporating reaction outcome prediction methodology and standardized synthesis automation. The successful candidate will be supported by, and work collaboratively with Professor Jeffrey Bode at the ETH in Zürich and Synple Chem in Kemptthal, Zürich. They will work closely with other researchers within the Bode group and the wider ETH community, as well as the Synple Chem team.

The overarching goal of this project is to bring together the Bode group's broad expertise in synthesis and reaction outcome prediction, and Synple Chem's synthesis automation, to improve and expand Synple Chem's existing synthesis automation platform by increasing throughput and improving the self-learning nature of the platform.The project will provide the opportunity to be involved with cutting-edge research across the fields of organic synthesis, chemistry automation, reaction informatics, and machine learning. The successful candidate will contribute to our development of a system for automating and accelerating hit discovery in pharmaceutical research.

The successful candidate will collaborate with synthetic chemists to tightly couple synthetic predictions and reaction automation. Some possible research topics include:

• Collaborations with synthetic chemists to optimize reaction conditions and generate the data to build effective AI/ML models for predicting whether a particular set of building blocks will work in a reaction
• Developing and applying innovative new active-learning strategies to support reaction optimization and the implementation of automation-friendly protocols
• Developing new systems for capturing, managing, querying, and exploring the experimental data generated during the reaction optimizations computational
• Expanding and refining existing pipelines for defining, enumerating, and screening virtual libraries based on the optimized reactions and available building blocks
• Developing approaches to allow the rapid inclusion of new reaction classes into the predictive models and automation protocols

• PhD in chemistry, data science, or a related field
• Extensive experience with Cheminformatics
• Experience with software development
• Solid understanding of organic chemistry and chemical processes
• Experience with modern AI/ML approaches
• Understanding of basic automation techniques, databases, and data analysis tools
• Excellent written and verbal communication skills (English)

• Opportunity to conduct research at the interfaces of several hot fields: AI-assisted drug discovery, virtual screening, and automated synthesis
• Working collaboratively with both synthetic and computational chemists from academic research groups and industry
• An applied research project with high-impact scientific and commercial goals
• A highly supportive, multidisciplinary team environment