Small Molecule Computational Scientist

About the role

The Small Molecule Computational Scientist operates at the intersection of computational chemistry, cheminformatics and machine learning, supporting both Boltz's internal research and external drug‑discovery collaborations by building and curating datasets, evaluating and improving models, developing scientific tooling, and translating large‑scale molecular analyses into actionable insights for research road‑maps and discovery decisions.

About the company

Boltz is a public-benefit company developing AI-powered molecular modelling tools to make biology programmable and accelerate drug discovery; its open models (Boltz-1, Boltz-2, BoltzGen) are trusted by biotech, academia and leading pharmaceutical, agricultural, and industrial research organisations.

Requirements

• PhD or equivalent experience in computational chemistry, cheminformatics, chemical biology, structural bioinformatics, or a closely related field
• Strong Python programming skills; ability to build clean, reusable scientific tooling and experience with RDKit
• Deep understanding of small‑molecule chemistry, including functional groups, stereochemistry, protonation, tautomers, scaffolds and molecular similarity
• Proficiency working with protein sequence and structural data, protein‑ligand complexes, binding sites, residue mappings and similarity assessments
• Highly proficient at analysing large molecular datasets with experience in molecular fingerprints, similarity search, clustering, scaffold analysis, dimensionality reduction, diversity selection, sampling and chemical‑space visualisation
• Understanding of experimental binding and screening measurements (KD, Ki, IC50, EC50) and ability to consider assay context, uncertainty, replicates, censoring and comparability
• Strong communication skills
• (Preferred) Experience supporting real drug‑discovery programs such as virtual screening, hit discovery, hit‑validation, hit‑to‑lead or lead optimisation
• (Preferred) Experience handling large chemical libraries or model‑generated datasets, including clustering, filtering, diversity selection, compound prioritisation and chemical‑space coverage analysis
• (Preferred) Experience with molecular machine learning for affinity/property prediction, virtual screening, molecular representations or generative design
• (Preferred) Contributions to open‑source scientific software