About the role
Description
Build computational tools and scientific AI agents that turn complex mass spectrometry data into molecular identities, quantitative measurements, and insights into drug translation.. Work with experimental scientists to develop reliable analytical workflows and training environments that teach frontier models to reason about chemistry.
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 computational tools and AI agents for LC-MS/MS feature detection, peak alignment, molecular identification, quantification, and quality control.
- Develop agents that predict molecular fragmentation and identify structures by combining mass spectra, chromatography, UV, and NMR evidence.
- Solve complex mixture analysis problems, including overlapping peaks, background interference, matrix effects, and uncertain compound identities.
- Build reliable workflows for relative and absolute quantification, accounting for calibration, measurement uncertainty, and compound-dependent signal responses.
- Combine analytical chemistry expertise with agents to investigate drug metabolism, identify reactive metabolites, and interpret drug-induced metabolic changes.
- Work with experimental scientists to generate datasets and verified reference measurements that reveal where computational methods and agents succeed or fail.
- Turn these experiments into benchmarks and reinforcement learning environments that teach frontier models increasingly complex chemical reasoning and analysis.
- Integrate metabolomics with imaging, transcriptomics, and proteomics to uncover mechanisms of drug toxicity and guide further experiments.
What we look for
- Deep experience in computational LC-MS/MS, particularly untargeted metabolomics and complex mixture analysis.
- Strong programming skills and a track record of building reliable scientific software.
- A strong foundation in analytical chemistry, ionization, fragmentation, chromatography, and the physics of mass spectrometry.
- Experience developing algorithms or extending tools such as MZmine or OpenMS to solve challenging analytical problems.
- Excitement about building and using AI agents to interpret experimental data, test chemical hypotheses, and automate scientific analysis.
- Rigorous judgment about data quality, measurement uncertainty, and the evidence needed to support a molecular identification or biological conclusion.
- Curiosity and ownership, with a desire to work closely with experimental scientists and see your methods improve real experiments.
Technical skills we value
- Python, NumPy, SciPy, pandas, SQL, and reproducible scientific software development; C++ is a plus.
- LC-MS/MS processing, including feature detection, peak integration, alignment, deconvolution, isotope and adduct annotation, and quality control.
- Untargeted metabolomics, spectral library matching, fragmentation prediction, molecular identification, and quantitative analysis.
- Tools and formats such as MZmine, OpenMS, MS-DIAL, SIRIUS, GNPS, and mzML.
- Cheminformatics and molecular representations, including RDKit, SMILES, molecular fingerprints, and structure similarity.
- LLM APIs, agent tool development, scientific data retrieval, and automated analysis workflows.
- Agent evaluation, trace analysis, and benchmarks with experimentally verified answers and uncertainty-aware scoring.
- Statistical methods for calibration, batch correction, differential abundance, and integration with imaging, transcriptomics, and proteomics.