Research Scientist, Medical World Models (AI)

Location: Remote in the United States or Canada

Company

hirify.global builds a proactive, data-driven healthcare platform that combines blood tests, imaging, biomarkers, questionnaires, and wearable data to generate clinically meaningful health insights.

What you will do

• Design and train models that represent members’ current health states and forecast future states from irregularly sampled longitudinal data.
• Develop multimodal encoders that combine imaging, biomarkers, questionnaires, EHR data, and other medical modalities while handling missing inputs.
• Build evaluation frameworks with validation sets, confidence intervals, calibration measures, forecasting metrics, error analysis, and collapse diagnostics.
• Own training and evaluation code, including data loaders, distributed multi-GPU training, experiment tracking, versioned releases, model cards, and licence inventories.
• Deliver documented pretrained encoders and forecasters to product-track teams and support clinical validation and hand-off to Engineering and Product Development.
• Collaborate with ML engineers, data and infrastructure teams, quality and regulatory specialists, and clinicians; contribute to research practices and hiring.

Requirements

• PhD in machine learning, computer science, biomedical engineering, or a related field with 1–2+ years of professional experience, or MS/BS with 5+ years building and evaluating ML models on real data.
• Depth in temporal or longitudinal modeling, self-supervised or foundation-model pretraining on medical imaging or multimodal data, or multimodal fusion of imaging with tabular, EHR, or biomarker data.
• Strong Python and PyTorch skills, experience with multi-GPU training and large datasets, and ability to write reusable production-quality code.
• Strong statistical and evaluation skills, including calibration, error analysis, and validation design.
• Publication record at leading ML or medical-imaging venues, or equivalent research output delivered into production.
• Clear written and verbal communication with technical and clinical audiences.

Nice to have

• Experience with world models, latent dynamics, model-based reinforcement learning, or counterfactual and causal inference on observational health data.
• Experience with longitudinal cohorts, biobank-scale data, EHR or laboratory time series, tabular foundation models, normative modeling, or biological age estimation.
• Experience with vision-language pretraining, radiology reports, LLM-based report information extraction, AWS, Databricks, or regulated healthcare environments.
• Experience as a founding or early member of a research team.

Culture & Benefits

• Remote work flexibility within the United States or Canada.
• Opportunity to publish research and build models intended for large-scale clinical use.
• Stock options and comprehensive health, dental, and vision plans for employees and families.
• Wellness and commuter benefits plus a competitive vacation policy.
• Learning-focused, collaborative environment with scientists, engineers, and clinicians.