Chemical data scientist

Variational AI is building a generative foundation model to accelerate small molecule drug discovery. This role focuses on curating and preparing chemical and biological datasets, designing featurizations, and integrating data into machine learning pipelines. You will collaborate with ML scientists, computational chemists, and medicinal chemists to improve predictive and generative models.

• Identify, curate, and prepare datasets ranging from potency and ADMET to gene expression and cell painting
• Characterize errors and noise in datasets, and develop techniques to filter and clean them
• Analyze curated datasets and integrate chemical data into machine learning algorithms by designing data loaders
• Develop ligand- and structure-based featurizations
• Apply traditional cheminformatics techniques

• B.S., M.S., or Ph.D. in data science, statistics, computer science, physics, or related discipline with experience analyzing messy datasets
• B.S., M.S., or Ph.D. in chemistry or a related discipline with experience in cheminformatics
• Demonstrated skill in chemical informatics including aggregation, curation, and preparation of large experimental datasets from multiple sources
• Strong programming skills in Python and experience with cheminformatics libraries and data analysis tools (RDKit, Matplotlib, pandas, seaborn)