Computational Scientist (Medicinal Chemistry)

Job description

Charter Be a founding member of the team building the first accurate AI systems for replacing animal and legacy toxicity experiments with human-relevant predictive models. You will help Axiom answer one of the most important questions in drug discovery: - Given a molecule’s structure, potency, exposure, and biological response, will it be safe enough in humans? And, eventually: - How should we change the molecule to make it safer while preserving efficacy? About Axiom Axiom is building an ecosystem to compound technology which will replace animal testing and, over time, reshape how clinical trials are run. We partner with leading organizations to transform capital into proprietary data and machine learning models, then deploy those models across the world’s largest pharmaceutical companies to improve how medicines are discovered and developed. It starts with deeply understanding the needs of drug hunters inside large pharma, especially around drug toxicity and safety. Those needs shape the world-class datasets we build from scratch. We then use that data to advance our own ML research, while also collaborating with leading AI labs to improve frontier models’ ability to reason over Axiom’s data inside Axiom’s agent harness. This creates a compounding loop: deeper customer understanding shapes the data we generate; better data improves frontier models, Axiom’s fine-tuned models, and our agentic infrastructure; stronger models and tooling expand the capabilities we can offer; and those capabilities are forward deployed into pharma's drug discovery workflows, where scientists use them to solve the highest value drug discovery problems. In turn, this helps us identify the next problems to tackle. Today, we are focused on solving drug-induced liver injury through an integrated data and agentic system already being used by 7 of the top 20 pharma companies and several of the world’s most innovative biotechs. Over time, Axiom will invest billions into the world’s largest human datasets across all the major organ systems, paired with an agentic harness that uses this data to predict human drug outcomes dramatically better than animals and phase 1 clinical trials. What you will do You will sit at the center of Axiom’s chemistry, biology, modeling, and customer work. - 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. What we are looking for We are looking for someone who can combine medicinal chemistry judgment with computational depth. - You have an advanced degree in chemistry, computational chemistry, cheminformatics, medicinal chemistry, chemical biology, or equivalent experience inside a drug discovery organization. - You might identify as a computational chemist, cheminformatics scientist, ML for chemistry researcher, medicinal chemist with strong computational skills, or drug discovery scientist who became deeply technical. - You understand how real drug programs move from hit discovery to lead optimization to candidate selection. - You can reason about potency, selectivity, physicochemical properties, ADME, PK, exposure, safety margins, and clinical translatability. - You are excited by the challenge of connecting chemical structure to human outcomes. - You understand the limitations of current preclinical safety models and have strong opinions about how they should be improved. - You are comfortable analyzing large chemical datasets and drawing conclusions from a combination of data science, chemistry, and biological reasoning. - You can work directly with pharma customers, earn the trust of senior drug hunters, and communicate technical insights clearly. - You want to build tools that are not just scientifically interesting, but actually used to make decisions in real drug discovery programs. Technical skills we value We do not expect every candidate to have all of these, but we are especially excited by experience with: - 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