Computational Scientist (Medicinal Chemistry)

About the role

You will sit at the center of Axiom’s chemistry, biology, modeling, and customer work. You will lead the analysis of model outputs across chemical series, targets, modalities, mechanisms, and clinical toxicity endpoints. You will identify where Axiom’s models perform well, where they fail, and what those failures reveal about chemistry, biology, exposure, or missing data. You will work with ML researchers to improve models that predict human toxicity as a function of chemical structure, in vitro potency, biological response, dose, Cmax, ADME, and clinical context. You will analyze large-scale chemistry datasets across thousands to hundreds of thousands of compounds for model training, evaluation, benchmarking, and dataset design. You will clean, curate, and structure chemical data, including compound identifiers, structures, salts, stereochemistry, dose/exposure information, ADME properties, targets, annotations, and clinical outcomes. You will use medicinal chemistry intuition to interpret model predictions, understand structure-toxicity relationships, and identify chemically meaningful patterns. You will partner directly with top drug hunters at leading pharma and biotech companies to interpret model outputs and help them make better program decisions. You will help design new experimental and molecular datasets based on model failures, customer needs, chemical space gaps, and real-world drug discovery use cases. You will work with Axiom’s mechanistic agent to connect chemical structure, biological readouts, phenotypic similarity, clinical outcomes, and proposed mechanisms of toxicity. You will influence active drug programs by helping teams understand whether toxicity risk is driven by exposure, potency, off-target biology, reactive metabolites, transporters, mitochondrial liability, cholestasis, immune mechanisms, or other drivers. You will shape Axiom’s product by translating customer feedback into better model outputs, visualizations, analyses, and workflows for medicinal chemists and toxicologists. You will help define how the best drug hunters in the world will use AI to design safer medicines.

Responsibilities

• Lead the analysis of model outputs across chemical series, targets, modalities, mechanisms, and clinical toxicity endpoints.
• Identify where Axiom’s models perform well, where they fail, and what those failures reveal about chemistry, biology, exposure, or missing data.
• Work with ML researchers to improve models that predict human toxicity as a function of chemical structure, in vitro potency, biological response, dose, Cmax, ADME, and clinical context.
• Analyze large-scale chemistry datasets across thousands to hundreds of thousands of compounds for model training, evaluation, benchmarking, and dataset design.
• Clean, curate, and structure chemical data, including compound identifiers, structures, salts, stereochemistry, dose/exposure information, ADME properties, targets, annotations, and clinical outcomes.
• Use medicinal chemistry intuition to interpret model predictions, understand structure-toxicity relationships, and identify chemically meaningful patterns.
• Partner directly with top drug hunters at leading pharma and biotech companies to interpret model outputs and help them make better program decisions.
• Help design new experimental and molecular datasets based on model failures, customer needs, chemical space gaps, and real-world drug discovery use cases.
• Work with Axiom’s mechanistic agent to connect chemical structure, biological readouts, phenotypic similarity, clinical outcomes, and proposed mechanisms of toxicity.
• Influence active drug programs by helping teams understand whether toxicity risk is driven by exposure, potency, off-target biology, reactive metabolites, transporters, mitochondrial liability, cholestasis, immune mechanisms, or other drivers.
• Shape Axiom’s product by translating customer feedback into better model outputs, visualizations, analyses, and workflows for medicinal chemists and toxicologists.
• Help define how the best drug hunters in the world will use AI to design safer medicines.

Requirements

• Advanced degree in chemistry, computational chemistry, cheminformatics, medicinal chemistry, chemical biology, or equivalent experience inside a drug discovery organization.
• Experience with Python, Pandas, NumPy, SciPy, scikit-learn, Jupyter notebooks, RDKit, Datamol, DeepChem, or related cheminformatics tooling.
• Experience with chemical structure processing, standardization, salt stripping, stereochemistry handling, scaffold analysis, similarity search, clustering, and molecular fingerprints.
• Experience with large-scale chemical dataset curation and quality control, QSAR, molecular property prediction, ADME modeling, exposure modeling, or toxicity prediction.
• Experience with dose-response modeling, curve fitting, calibration, benchmarking, uncertainty analysis, and model error analysis.
• Experience with SQL, cloud data workflows, and large-scale data processing.
• Experience with drug discovery datasets involving targets, assays, potency, selectivity, ADME, PK, toxicology, or clinical outcomes.
• Experience in scientific presentation and storytelling for medicinal chemists, toxicologists, and drug discovery leadership.

Qualifications

• Comfortable analyzing large chemical datasets and drawing conclusions from a combination of data science, chemistry, and biological reasoning.
• Ability to work directly with pharma customers, earn the trust of senior drug hunters, and communicate technical insights clearly.
• Passion for building tools that are not just scientifically interesting, but actually used to make decisions in real drug discovery programs.

Skills

• Python, Pandas, NumPy, SciPy, scikit-learn, Jupyter notebooks
• RDKit, Datamol, DeepChem, or related cheminformatics tooling
• Chemical structure processing, standardization, salt stripping, stereochemistry handling, scaffold analysis, similarity search, clustering, and molecular fingerprints
• Large-scale chemical dataset curation and quality control
• QSAR, molecular property prediction, ADME modeling, exposure modeling, or toxicity prediction
• Dose-response modeling, curve fitting, calibration, benchmarking, uncertainty analysis, and model error analysis
• SQL, cloud data workflows, and large-scale data processing
• Drug discovery datasets involving targets, assays, potency, selectivity, ADME, PK, toxicology, or clinical outcomes
• Scientific presentation and storytelling for medicinal chemists, toxicologists, and drug discovery leadership