Computational Scientist

About the role

Axiom is a founding team building an ecosystem to replace animal testing and transform clinical trials through agentic systems that predict human outcomes. You will join a mission to create the world largest human datasets across major organ systems, starting with drug-induced liver injury.

Key facts

What you'll do

• Manage and scale the computational mass spectrometry stack.
• Process large-scale biological mass spectrometry data including proteomics, metabolomics, lipidomics, and reactive metabolite workflows.
• Build and maintain pipelines for untargeted LC-MS/MS using tools like MS-DIAL, MZmine, GNPS, OpenMS, or Skyline.
• Create workflows for peak detection, batch correction, normalization, alignment, QC, and feature filtering.
• Transform raw mass spec outputs into representations compatible with machine learning models and mechanistic reasoning agents.
• Partner with lab, chemistry, biology, and engineering teams to refine high-throughput LC-MS/MS assays.
• Derive biological insights regarding metabolic signatures, pathway changes, and toxicity mechanisms.
• Construct datasets linking chemical structure, dose, cellular phenotype, and human toxicity outcomes.
• Implement quality control systems to monitor instrument performance, drift, sample quality, and annotation confidence.
• Work with ML researchers to improve toxicity prediction models and investigate model errors.
• Design strategies to expand data generation based on customer needs and model performance.

Requirements

• Proven experience building computational workflows for untargeted LC-MS/MS metabolomics.
• Ability to use mass spectrometry data to address complex biological questions.
• Deep understanding of mass spec data challenges including isotopes, adducts, batch effects, retention time drift, and instrument artifacts.
• Proficiency in moving from raw data files to biological interpretation.
• Knowledge of lipid biology, metabolism, protein changes, and drug-induced cellular stress.
• Experience building scalable infrastructure rather than one-off analysis.
• Ability to collaborate with wet lab scientists to debug assays and improve experimental design.
• Commitment to scientific rigor, reproducibility, and data quality.

Skills & tools

• LC-MS/MS
• MZmine
• OpenMS
• MS-DIAL
• GNPS
• Skyline
• Metabolomics
• Lipidomics
• Proteomics
• Machine Learning
• Computational Pipeline Development

Practical notes

This is a founding team role focused on replacing animal testing and reducing clinical toxicity failures. Applicants should be prepared to take ownership of a core scientific modality within an early-stage company environment.