Lead​/Senior Machine Learning Scientist, Integrative Phenotyping

Position: Lead/ Senior Machine Learning Scientist, Integrative Phenotyping
The Opportunityinsitro is a physical AI company dedicated to unlocking causal human biology and accelerating the delivery of better medicines to patients. Our unique Virtual Human platform identifies novel, high-impact genetic intervention points, which our TherML platform translates into therapeutics—whether small molecules, biologics, or oligos. With multiple programs in metabolic disease and neuroscience advancing toward the clinic, and our first IND submission slated for the second half of this year, we are at a pivotal inflection point.

As a Lead/ Senior Machine Learning Scientist on the Integrative Phenotyping team, you will develop, product ionize, and deploy cutting-edge ML approaches to build precise phenotypes from large-scale multimodal datasets — clinical imaging, electronic health records, longitudinal outcomes, biomarkers, and multi-omic readouts — and use them to understand patient state, predict clinical endpoints, and identify therapeutic targets. You’ll work alongside machine learning scientists, statistical geneticists, life scientists, software engineers, and clinicians, and your expertise will shape how the company builds rigorous ML on complex human data.

Based in South San Francisco, this position reports directly to the Head of Integrative Phenotyping and offers an in-person hybrid schedule of three days per week.

Responsibilities ML Methods & Platform Build Precise Phenotypes:
Develop and deploy ML methods that extract biological insight from complex, high-dimensional human cohort data such as MRI and functional genomics.

Model Patient State:
Develop models that characterize patient state and predict outcomes and clinical endpoints from multimodal data including clinical imaging, EHRs, longitudinal outcomes, biomarkers, and multi-omic readouts.

Set the Bar:
Ensure modeling strategies are rigorous, effective, and aligned with best practices in the field.

Engineer Reusable Components:
Build robust, reusable platform components in partnership with the software engineering team.

Target Discovery & Translation Integrate Causal Evidence:
Combine causal, multimodal analyses across diverse phenotypic readouts to select better therapeutic targets.

Biomarkers & Endpoints:
Partner with Therapeutic Area and Clinical Development colleagues to develop new biomarkers for patient selection and clinical endpoints.

Connect Genetics to Phenotypes:
Work with the Statistical Genetics team to associate human genetics with ML-derived phenotypes.

About You Experience & Qualifications Proven Tenure:
PhD in computer science, machine learning, or a related field, or 5+ years of equivalent applied ML research experience.

Modern ML Expertise:
Hands-on experience developing and deploying state-of-the-art ML methods, including multimodal techniques, to extract clinically relevant signals from complex data.

Clinical Data Depth:

Experience with several of: clinical imaging (e.g., MRI, DEXA, CT, echocardiography), clinical records (e.g., EHRs, medications, outcomes), physiological recordings (e.g., EEG, ECG), or biobank-scale human genetic data.

Multimodal

Experience:

Experience with high-content modalities such as single-cell or bulk omics, genetic perturbation screening, spatial proteomics, or pooled optical screening.

Publication Record:
Meaningful, high-quality contributions in ML, ML for health, computational biology, or biomedical venues.

Engineering Fluency:
Strong Python in a cloud environment and modern deep learning frameworks, with a track record of reusable, tested, version-controlled ML code.

Core Competencies End-to-End Delivery:
You work with other ML scientists and engineers to take a real-world problem from sourcing and qualifying training data through model design, testing, and benchmarking.

C…