Post Doctoral Fellow – Computational Modeling and Machine Learning

Post Doctoral Fellow – Computational Modeling and Machine Learning

Requirements

• Currently holding a Ph.D. (or must receive by the time of the start date) in chemical engineering, chemistry, computational/theoretical chemistry, or a related field.
• Proficient understanding of synthetic reaction transformations and in-depth expertise in mechanistic analysis.
• Familiarity with Deep Learning architectures, including Graph Neural Networks (GNNs), active learning, and reinforcement learning.
• Strong background in computational chemistry, with a proven track record of applying computational techniques to address complex chemical challenges.
• Demonstrated proficiency in programming (Proficient in Python), exemplified by successful completion of university coursework or a compelling portfolio showcasing previous code projects.
• Excellent written and oral communication skills
• Ability to interact with different interlocutors, in particular development teams (data engineering, ITS and Architecture / Ops teams)

Responsibilities

• Build an artificial intelligence/machine learning (AI/ML) model capable of generating reaction networks based on existing chemical knowledge. This involves integrating quantum chemistry tools, external databases, and literature data to provide comprehensive lists of possible reactions for specified starting materials, reagents, and catalysts.
• Develop and apply filters/rules based on thermodynamics and reaction feasibility to refine and narrow down generated reaction networks.
• Implementing and optimizing active learning algorithms to guide the selection of experiments, ensuring efficient data acquisition and model improvement.
• Collaborate closely with fellow data scientists and experimentalists to seamlessly integrate the developed tool into an automated AI-assisted kinetic learning algorithm.

Preferred Qualifications

No preferred qualifications provided.