Computational Scientist (Biology)

Axiom Bio; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Axiom Bio in San Francisco is seeking a biology-focused ML/data scientist to advance our closed-loop toxicology AI platform. You will analyze multimodal toxicity datasets, extract actionable signals, and bridge wet-lab data with machine learning to model mechanisms of drug-induced toxicity.

You will collaborate with ML researchers, develop high-content imaging assays, and help build scalable data pipelines for predicting safety profiles in drug development.

Qualifications

• Solid mathematical and statistical background in data analysis, modeling, and statistics.
• Experience with high-content imaging and image analysis workflows.
• Proficiency with CellProfiler/Cellpose for imaging data analysis.
• Experience with high-throughput screening and assay development.
• Ability to bridge biology and machine learning through coding.
• Strong track record of publishing scientific work.

Responsibilities

• Drive exploration and analysis of multimodal toxicity datasets.
• Transform high-dimensional biological data into clear, actionable signals.
• Analyze ML models to understand learned features and failure modes.
• Develop methods at the intersection of computation and biology to understand biological mechanisms.
• Model relationships between chemical structures and biological responses.
• Collaborate with ML researchers to improve model accuracy.
• Develop high-content imaging assays for predictive tissue toxicity datasets.
• Create quality control processes for large imaging datasets.
• Support drug discovery teams in understanding toxicity profiles.

Skills

Mathematical statistics

Imaging data analysis

Cellprofiler

Cellpose

High content imaging

Cell painting

Assay development

High throughput screening

Automation

Strong coding ability

Biology & CS bridging

Tools

Cellprofiler

Cellpose

Job description

Axiom is building the closed-loop scientific AI system required to replace animal testing and, over time, much of human safety testing. We start with pharma’s hardest drug development toxicology problems. Those problems define the proprietary human biological data we generate through Axiom’s Data Factory. We use that data to train scientific AI, partnering with leading AI labs to improve frontier models while building our own specialist agentic harness to deploy the improved frontier models back into pharma. Each deployment reveals the next capabilities to build, creating a compounding loop across data, models, and drug development. Today, liver toxicity is our proving ground. Axiom is already helping leading pharmaceutical companies understand toxicity, identify its mechanism, and design safer drugs. Over time, we will expand across the major organ systems and build the experimental and agentic system of record for translational drug development. Our goal is to dramatically reduce the risk of testing new molecules in humans, enabling high throughput evaluation of efficacy in humans.

What are we looking for:

We want to hire people who inspire us and level up the entire team. They should be high energy, high agency, and have great taste for what matters. They should have a relentless “observe, orient, decide, act” loop, and be constantly identifying what needs to happen and getting it done. They need to be technically excellent and obsessive masters of their craft, as well as having a great curiosity which will keep them at the frontier of tech and help them interface between AI, engineering, product, biology, chemistry, and business. They could work in big tech, but it won’t satisfy them. They want to go on an adventure which will be brutally challenging, and to share in the rewards and satisfaction at its end.

What you will do:

• Drive the exploration and analysis of the world's largest multimodal toxicity datasets
• Transform noisy, high-dimensional biological data into clear, actionable insights by identifying critical signals
• Conduct detailed analyses on machine learning models to understand what the model has learned and its failure modes
• Develop new methods at the intersection of computation and biology to understand biological mechanisms.
• Investigate a diverse range of biological systems—including liver, heart, kidney, and immune tissues—to model the relationship between chemical structures and biological responses.
• Collaborate with ML researchers to enhance model accuracy
• Develop new high content imaging assays capable of generating datasets for predictive modeling of human tissue toxicity
• Create quality control processes for massive high content imaging datasets.
• Help leading drug discovery teams build a deep understanding of drugs’ toxicity profiles

We’re especially interested in:

• Solid mathematical and statistical background (curve fitting, dimensionality reduction, statistics, machine learning, imaging algorithms)
• Cellprofiler, Cellpose, imaging data analysis, quality control
• High content imaging, cell painting, assay development
• High throughput screening, automation

What we look for:

• Strong coding ability for a biologist - you may straddle biology and computer science/machine learning, or you may have taught yourself to code to help with your analysis
• A talent for identifying signals in biological data and for separating signal from noise
• A drive to push beyond conventional methods to develop new and better computational algorithms and approaches for biology
• Passionate about high-content imaging and about building, understanding, and evaluating biological datasets
• Driven by a relentless pursuit of scientific excellence— impeccable data quality, meticulous analyses, and well-grounded conclusions
• Ability to bridge wet lab protocols, computational analysis, and machine learning algorithms
• Obsessive technical curiosity for all things in the wetlab, drylab, and drug discovery.
• Strong research and publication track record
• Strong ability to communicate and inspire with science