Computational Scientist, Biology

Axiom Bio; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Axiom Bio is building a high-throughput liver safety platform that blends biology and AI to predict drug toxicity. You will analyze multimodal datasets, identify mechanisms of injury, and drive reproducible workflows across imaging, transcriptomics, and mass spectrometry.

You will partner with ML scientists to refine models, interpret signals, and propose additional measurements to close gaps. Join a mission to make medicines safer through data-driven insights.

Qualifications

• Strong background in integrating biology with ML and data analysis.
• Ability to work with large, multimodal datasets and extract robust features.
• Experience in QC, reproducibility, and experimental variability assessment.
• Comfort interpreting model predictions with mechanistic biology context.

Responsibilities

• Lead the analysis of multimodal toxicity datasets to derive biological insights.
• Characterize drug responses in primary human cells and multicellular systems.
• Develop QC methods for batch effects and assay performance.
• Collaborate with ML scientists to improve predictive models.
• Investigate model behavior and identify failure modes.
• Design protocols and assays to capture relevant biology.
• Interpret compound toxicity and inform drug development decisions.
• Help build AI systems that explain mechanisms and weigh evidence.

Skills

Python + scientific stack

High-content imaging

Statistical modeling

Image analysis tools

Tools

CellProfiler

Cellpose

napari

OpenCV

scikit-image

Pandas

NumPy

SciPy

Job description

Turn large-scale imaging, molecular, and biochemical data into insights that explain drug toxicity and improve predictions of human response to scientists at the world’s largest pharmaceutical companies and AI labs. Uncover mechanisms of injury, identify model failures, and shape the experiments that make Axiom’s scientific agents insanely accurate at predicting 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:

• Lead the analysis of large, multimodal toxicity datasets, turning noisy, high-dimensional imaging, transcriptomic, proteomic, and biochemical measurements into biological insights and features for predictive models.
• Characterize drug responses in primary human cells and multicellular systems, identifying phenotypes associated with mitochondrial dysfunction, cholestasis, lipid accumulation, ER stress, and many other mechanisms of injury.
• Develop rigorous quality control methods to assess reproducibility, batch effects, assay performance, and experimental variability across modalities.
• Partner with ML scientists to improve models and scientific agents that predict drug toxicity, testing whether their predictions reflect meaningful biology and generalize to new compounds.
• Investigate model behavior, interpret biological signals, and identify failure modes. Propose additional measurements to address gaps and lead pilot studies to test their value.
• Work with experimental scientists to design protocols and assays that capture relevant biology and measurably improve predictive performance.
• Partner with leading pharmaceutical and biotech teams to interpret compound toxicity profiles, explain the evidence behind model predictions, and inform drug development decisions.
• Help build AI systems that move beyond toxicity classification to explain mechanisms, weigh evidence, and guide the design of safer drugs.

What we look for:

• You combine deep biological understanding with exceptional computational ability.
• You’re a biologist with strong computational skills or a computational scientist with deep biological fluency. You work directly with raw experimental data and understand how it was generated.
• You find meaningful signals in complex, noisy biological data. You have strong statistical judgment and can distinguish biological effects from confounding, artifacts, and spurious correlations.
• You hold your work to rigorous standards for data quality, reproducibility, and scientific evidence.
• You connect experimental biology with machine learning, understanding how protocols, assay design, feature extraction, and modeling choices shape the conclusions a system can support.
• You’re curious about high-content imaging, transcriptomics, and assay development, with the desire to investigate diverse mechanisms of toxicity across the liver, kidney, heart, and immune system and pharmacokinetics.
• You can critically evaluate how AI models and agents interpret biological evidence, identify where their reasoning fails, and design experiments and datasets that address those gaps.

Technical skills we value:

• Strong Python programming and scientific software development, including pandas, NumPy, SciPy, scikit-learn, and reproducible analytical workflows.
• Statistical inference, experimental design, variance decomposition, dose-response modeling, dimensionality reduction, and predictive modeling with rigorous evaluation.
• High-content imaging analysis, morphological profiling, and image-based phenotyping.
• Image analysis tools such as CellProfiler, Cellpose, napari, OpenCV, and scikit-image.
• Analysis and integration of transcriptomic, proteomic, mass spectrometry, ADME, and other complex biological datasets.
• High-throughput screening, assay development, laboratory automation, and methods for assessing experimental quality.
• Biological interpretation of model predictions, including identifying confounding factors, failure modes, and limits to generalization.
• Clear scientific communication that turns complex analyses into compelling explanations grounded in evidence.