You will work closely with team members from the cheminformatics teams as well as the software engineering, process engineering, and chemistry teams to contribute to the development of the most efficient, automated, and versatile chemical manufacturing laboratory in the world.

Responsibilities

• Prepare, process, clean, and annotate datasets for machine learning development; curate datasets for company-wide use.
• Influence data ingestion engines to ensure pristine and well annotated data for short- and long-term applications are systematically acquired from the laboratory or third-party sources
• Develop, benchmark, and rapidly iterate on deterministic and AI/Deep Learning methods for template-based and template-free retrosynthesis towards continuously improving performance.
• Develop, benchmark, and rapidly iterate on AI methods for reaction likelihood estimation.
• Design, test and implement algorithms for chemical space exploration and optimise synthetic campaigns.
• Development and implementation of R&D algorithms into software products.
• Presentation of data and recommendations to the Chemify executive team and customers, internal and external.
• Contribute across the company as need arises.

Requirements

• PhD degree in Data science/AI, Computer Science, Cheminformatics, Bioinformatic, or equivalent professional experience.
• Minimum 5+ years of experience using major deep learning framework.
• Successful development and deployment of AI/ML/DL based tools in high-value applications.
• Deep domain expertise in applied mathematics and primitives used in AI/ML/DL
• Cross-functional inclination to partner with strong software engineers
• Knowledge of cheminformatics and retrosynthesis.
• Strong proficiency with ML toolkits (Pytorch, Tensorflow, Scikit-Learn, etc) and deployment of software on high-performance compute clusters.
• Understanding of the latest AI research and ability to efficiently implement these systems.
• Strong analytical thinking skills and the capacity to approach challenges methodically.
• Proficiency with cloud platforms like AWS for ML applications.
• Enthusiasm to learn new approaches and concepts and to work with an experimental automation platform.
• Keen interest in chemistry and willingness to learn chemical concepts fast.
• Proficiency in contemporary software engineering approaches, including CI/CD, version control, and unit testing.
• Excellent oral and written communication & presentation skills (English fluency)

Desired skills & attributes

• Experience successfully building computational retrosynthesis a plus
• Experience with RDkit toolkit and reaction SMARTS syntax.
• Experience in the development & deployment of large-scale ML algorithms.
• Experience leading interdisciplinary teams to deliver results under tight deadlines, preferably using Agile/Scrum-based project management.
• Experience analysing large structured and unstructured datasets.
• Familiarity with database tools such as RDBMS (e.g. MySQL) or NO-SQL (e.g. MongoDB).
• Ability and eagerness to familiarize yourself with novel techniques based on project needs