Data Science & AI Innovation Postdoctoral Fellow in Machine Learning for Chemical Synthesis and Reactivity Prediction
Core
Develop and apply state-of-the-art predictive models using large-scale reaction datasets to improve chemical decision-making, reaction optimization, and molecular design for drug discovery.
Role type
Postdoctoral Research Fellow (AI/ML for Chemical Synthesis)
Builds
Predictive models for chemical reaction outcomes, conditions, and molecular reactivity
Domain
Biopharmaceuticals / Computational Chemistry / Machine Learning
Deliverable
production ML models
Required skills
Deep learning methods, Graph neural networks, Transformer architectures, Foundation models, Python programming, Statistical modeling, Large-scale data analysis
Preferred skills
Chemical reaction dataset curation, Relational database querying, Reaction encoding and atom mapping
Technologies
Graph neural networks, Transformers, Foundation models, Python
Responsibilities
Analyze large-scale chemical reaction datasets to identify trends and challenges; Develop, implement, and evaluate machine learning models for predicting reaction success and conditions; Benchmark state-of-the-art AI approaches against synthesis prediction tasks; Investigate novel pre-training strategies leveraging large-scale chemistry datasets; Collaborate with medicinal and synthetic chemists to address drug discovery challenges; Apply predictive models for substrate scope exploration and library synthesis design; Publish research findings in leading scientific journals.
Seniority
Postdoctoral Fellow (Early-career scientist immediately following PhD)