The posting
Description:
Build the data systems that turn Axiom’s laboratory, chemistry, and clinical data into reliable foundations for drug discovery and scientific AI. Combine strong engineering with rigorous statistics to catch errors, deliver reproducible datasets, and power the models and agents that predict human drug outcomes.
About Axiom:
Axiom’s mission is to eliminate unexpected drug toxicity and unlock an abundance of ultra safe medicines. We are starting with the liver, where toxicity remains a leading cause of drug failure. Our high-throughput human liver safety platform combines advanced human cell systems with imaging, transcriptomics, mass spectrometry, and drug metabolism measurements. Our AI agents integrate these data with chemical structure, human exposure, and thousands of clinical reference compounds to predict whether a drug will be toxic in humans, why, and how to make it safer.
We work with seven of the world’s top twenty pharmaceutical companies to design safety into molecules from the earliest stages. This applied work feeds directly into our partnerships with leading frontier AI labs, turning real discovery challenges and experimental feedback loops into scientific skill trees and reinforcement learning environments that train increasingly superhuman scientists. We then deploy these frontier models to make cancer therapies safer, unlock treatments for chronic diseases that demand exceptional safety, revive promising drugs abandoned because of toxicity, and much more.
Our ultimate ambition is to build a superhuman AI agent that predicts how a drug will behave across all major human organ systems before the first patient receives it. With insanely accurate safety predictions, we aim to enable rapid, high-throughput testing of novel drugs in humans with zero risk of toxicity. This is the key to unlocking an abundance of ultra safe, effective medicines.
What you will do:
- Build production-grade Python and SQL pipelines to ingest, process, validate, and serve high-content imaging, omics, mass spectrometry, and ADME data alongside chemical and clinical datasets.
- Own the shared data infrastructure that powers Axiom’s experiments, models, and scientific agents, including orchestration, storage, compute, isolated development environments, and continuous integration.
- Unify compound identities, sample histories, experimental metadata, and assay results across laboratories and sources, with reliable schemas, traceable transformations, and reproducible dataset versions.
- Develop statistically rigorous quality controls to detect missing data, anomalies, batch effects, and distribution shifts across imaging fields, wells, plates, and experimental batches.
- Build dashboards, monitoring, and alerts that help scientists identify experimental failures, diagnose pipeline issues, and act on data quality problems quickly.
- Give scientists, ML researchers, and AI agents reliable access to experimental data through well-designed tables, APIs, and analysis tools.
- Partner with laboratory and computational teams to investigate data and model failures, improve experimental workflows, and deliver validated datasets for modeling, evaluation, and agent training.
What we look for:
- Exceptional data engineering skills, strong computer science fundamentals, and a track record of building reliable, scalable systems with clear, maintainable code.
- Deep statistical understanding. You can explain a method’s assumptions, assess whether they hold, and recognize when its results are misleading.
- A strong instinct for correctness. You notice when numbers do not make sense, trace problems to their source, and build safeguards that prevent them from recurring.
- The ability to find meaningful signals in messy scientific data, choosing methods that fit the experimental design and distinguishing biological variation from technical artifacts.
- End-to-end ownership. You take ambiguous problems from raw data through validated outputs and understand how your work affects scientific and business decisions.
- Exceptional attention to detail and clear communication, with the ability to investigate problems alongside scientists, ML researchers, and engineers.
- Curiosity about experimental biology, chemistry, and drug discovery, and a drive to turn that understanding into better data systems and more reliable scientific AI.
Technical skills we value:
- Strong Python and SQL, scientific computing with NumPy and pandas, and analytical databases such as DuckDB or MotherDuck.
- Cloud infrastructure and reproducible compute using tools such as Modal, AWS, Docker, and Terraform.
- Data pipeline design, orchestration, schema design, automated validation, versioning, lineage, and observability.
- Statistical inference and experimental design, including hypothesis testing, multiple-testing correction, variance decomposition, and hierarchical modeling.
- Regression, classification, tree-based models, regularization, and cross-validation that respects experimental groups and batch structure.
- Model evaluation, including ROC-AUC, PR-AUC, calibration, precision and recall, leakage prevention, and the limitations of different metrics.
- Analysis and quality control of high-throughput screening, imaging, omics, mass spectrometry, and other high-dimensional scientific datasets.
- Chemical identifier harmonization and integration of compound, sample, assay, and clinical metadata. Prior biology experience is helpful but not required.
