Small Molecule Computational Scientist (AI)

Location: London, United Kingdom; hybrid working

Company

hirify.global is a public benefit company building AI-powered molecular modelling tools and open models for programmable biology and drug discovery.

What you will do

• Support internal research and external drug discovery programs through computational chemistry, molecular data analysis, and scientific tooling.
• Build datasets, evaluate models, investigate failure modes, and guide small-molecule modelling capabilities with Research and ML teams.
• Prepare, analyse, and interpret molecular and experimental data for pharmaceutical and biotechnology collaborations.
• Standardise and integrate small-molecule structures, protein data, protein–ligand complexes, binding measurements, screening data, and predicted properties.
• Analyse large molecular collections, screening libraries, generated compounds, protein families, and chemical series.
• Develop analyses that inform the research roadmap and real drug discovery decisions.

Requirements

• PhD or equivalent experience in computational chemistry, cheminformatics, chemical biology, structural bioinformatics, or a related field.
• Strong programming skills, particularly in Python, with experience building clean, reusable scientific tooling and using RDKit.
• Deep understanding of small-molecule chemistry, including molecular structures, functional groups, stereochemistry, protonation, tautomeric states, scaffolds, and molecular similarity.
• Experience with protein sequence and structural data, protein–ligand complexes, binding sites, residue mappings, protein constructs, and sequence or structural similarity.
• Proficiency in analysing large molecular datasets using fingerprints, similarity search, clustering, scaffold analysis, dimensionality reduction, diversity selection, sampling, and chemical-space visualisation.
• Understanding of binding and screening measurements including KD, Ki, IC50, and EC50, together with assay context, uncertainty, replicates, censoring, and measurement comparability.

Nice to have

• Experience supporting virtual screening, hit discovery, hit validation, hit-to-lead, or lead optimisation programs.
• Experience with large chemical libraries or model-generated molecular datasets.
• Experience with molecular machine learning, affinity or property prediction, virtual screening, molecular representations, or generative molecular design.
• Contributions to open-source scientific software.

Culture & Benefits

• Competitive compensation and equity in a public benefit company.
• London-based hybrid working.
• Opportunity to own a pipeline used by discovery teams and relied on by models and platforms.
• Small, high-calibre team that publishes its science.
• Learning budget, wellbeing support, and generous holiday allowance.