Computational Scientist (Biology)

Axiom•San Francisco, CA

57d

About The Position

At Axiom, we’re building the future of preclinical safety with AI models that predict human toxicity better than animal tests and legacy in vitro assays. We're looking for a computational biologist who thrives at the intersection of high-dimensional data, cell biology, and machine learning. You’ll work alongside a world-class team of scientists and engineers to develop predictive models from imaging and functional biochemical readouts—and use them to guide decisions in real-world drug development. This role is perfect for someone who’s excited to translate biological signal into actionable insights, shape the design of novel assays, and collaborate directly with leading pharma companies to make drug discovery faster, safer, and more human-relevant.

Requirements

Python, Pandas, Numpy, Jupyter Notebook
Solid mathematical and statistical background (curve fitting, dimensionality reduction, stats tests, modeling, traditional imaging algorithms)
Cellprofiler, Cellpose, imaging data analysis, quality control
High content imaging, cell painting, assay development
High throughput screening, automation
Biologist who taught themselves to code to do their own analysis.
You consistently impress fellow biologists with your coding abilities, setting a high standard that others aspire to match and/or envy.
Possess a unique talent for identifying intricate and subtle biological signals in imaging data, enhancing the accuracy and effectiveness of machine learning models to model the discovered signals.
Desire to continuously push beyond traditional methodologies to develop novel computational algorithms and approaches for biology.
Passionate about high-content imaging with a clear ambition to build the world’s largest and most comprehensive datasets.
Driven by a relentless pursuit of scientific excellence—dedicated to ensuring impeccable data quality, meticulous analyses, and only sharing data of the highest standards.
Exceptional ability to bridge the gap between wet lab protocols and machine learning algorithms, seamlessly integrating both fields to drive groundbreaking discoveries.
Obsessive technical curiosity for all things in the wetlab, drylab, and drug discovery.
Experience publishing and telling great scientific stories in a creditable + inspiring manner.

Responsibilities

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.
Uncover novel biological signals that differentiate safe and toxic drugs.
Conduct detailed error analyses on machine learning models to elucidate the biology captured by algorithms.
Invent cutting-edge algorithms at the intersection of computation and biology to model unexplored 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 by integrating newly discovered biological insights and data modalities.
Develop innovative high content imaging, mass spec, proteomics, and transcriptomic assays capable of generating unprecedented datasets for predictive modeling of human tissue toxicity.
Create quality control processes for massive, high throughput datasets.
Partner closely with leading drug discovery teams globally, empowering them with deep biological understanding of molecule toxicity profiles.