AI Biomarker Discovery Researcher

Orbio AI

Remote · $160k – $200k / 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

Finding a biomarker for early disease detection is a needle-in-a-haystack problem at genomic scale. A typical discovery project involves 500GB of multi-omics data, 50,000 candidate features, and the need to distinguish genuine biological signal from experimental noise. Our platform automates the pipeline from raw data to ranked biomarker candidates — but the ML methodology powering the ranking is where we need reinforcement. You'll design and implement the statistical learning models that score candidate biomarkers for predictive value, reproducibility, and pathway coherence. That means working with sparse, high-dimensional data where standard ML assumptions break down, and developing validation strategies that will satisfy FDA reviewers who are increasingly scrutinizing AI-derived findings. We have active collaborations with four top-10 pharma companies and two academic medical centers. Your models will directly inform which candidates advance to clinical validation. We publish and patent; you'll own your contributions.

Fully remote.

Responsibilities

Design statistical learning models for biomarker candidate scoring and ranking
Develop validation frameworks suitable for FDA regulatory scrutiny
Build feature selection pipelines for high-dimensional, sparse omics data
Implement reproducibility testing across independent cohorts
Collaborate with pharma partners on specific disease area requirements
Lead publication and patent documentation for novel methods

Requirements

6+ years in computational biology, bioinformatics, or ML applied to life sciences
Deep expertise in high-dimensional statistics and multi-omics data analysis
Strong Python skills with experience in PyTorch or scikit-learn
Understanding of clinical validation requirements and regulatory considerations
Publication track record in ML, bioinformatics, or computational biology