AI Patient Stratification Model Developer

Axion Labs

Remote · $100k – $130k / year · Full-time · Posted 4 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Clinical trials fail at 90% because the wrong patients are enrolled. Too much heterogeneity in the patient population masks treatment effects; too narrow enrollment criteria slow recruitment to a crawl and produce results that don't generalize. Patient stratification — identifying which patients are most likely to respond to a specific treatment — is one of the highest-value applications of ML in drug development. Our platform helps pharma companies design better trials by predicting which patient subgroups will respond, identifying biomarker signatures associated with responders, and simulating trial outcomes under different enrollment criteria. The models run on electronic health record data, genomic profiles, and historical trial results. You'll develop the stratification models for two new therapeutic areas currently in our pipeline — oncology and autoimmune disease. Each has different data modalities, different biomarker hypotheses, and different regulatory sensitivities.

Fully remote.

Responsibilities

Develop patient stratification models for oncology and autoimmune therapeutic areas
Build biomarker signature discovery pipelines from multi-modal clinical data
Implement trial simulation models evaluating enrollment criteria against outcome projections
Validate model outputs against external trial datasets and published literature
Collaborate with medical scientists to incorporate biological hypotheses into model design
Document model methodology in formats suitable for regulatory submission support

Requirements

3+ years in ML engineering with healthcare, clinical, or life sciences data experience
Experience with survival analysis, patient cohort modeling, or clinical trial statistics
Strong Python and statistical computing skills
Familiarity with EHR data structures or clinical data standards like OMOP
Ability to work with small, high-quality labeled datasets typical of clinical research