Senior AI Scientist: Digital Twins for Precision Medicine

AstraZeneca; Gaithersburg (MD); On-site; USD 140,000 - 180,000; Full time

Job summary

AstraZeneca in Gaithersburg, MD is seeking an exceptional Scientist or Senior Scientist to join the AI/ML for Translational and Clinical Sciences team, designing ML systems predicting clinical outcomes, discovering biomarkers, and enabling precision patient stratification across therapeutic areas.

You will build patient-level digital twins by integrating longitudinal clinical, imaging, genomic, proteomic, and real-world data, leveraging foundation models to inform trial design and translational

Qualifications

• PhD in Computer Science, ML, Computational Biology, Biomedical Engineering, Biostatistics, Physics, or related field OR MS with strong applied AI/ML healthcare experience.
• Demonstrated experience building ML/DL models for clinical/biomedical/omics data.
• Strong Python proficiency and experience with ML frameworks (PyTorch, JAX, TF) and distributed training.

Responsibilities

• Design, train, and validate patient-level digital twin models using multimodal longitudinal data.
• Contribute to foundation model research and evaluation for clinical/biomedical data.
• Build predictive and causal ML models for clinical endpoints and outcomes.
• Develop scalable pipelines for integrating structured clinical, omics, imaging, and real-world data.

Skills

Python proficiency

Transformer architectures

Statistical inference

Causal modelling

Survival analysis

Education

PhD in Computer Science / ML / Computational Biology / Biomedical Engineering

Tools

PyTorch

TensorFlow

JAX

Distributed GPU/TPU training

Job description

AstraZeneca in Gaithersburg, MD is seeking an exceptional Scientist or Senior Scientist to join the AI/ML for Translational and Clinical Sciences team, designing ML systems predicting clinical outcomes, discovering biomarkers, and enabling precision patient stratification across therapeutic areas.

You will build patient-level digital twins by integrating longitudinal clinical, imaging, genomic, proteomic, and real-world data, leveraging foundation models to inform trial design and translational