Senior Data Scientist

VA Boston Healthcare System; Boston (MA); On-site; USD 121,000 - 157,000; Full time

Benefits offered by this job

Dental insurance

Employee assistance program

Flexible spending account

Health insurance

Health savings account

Life insurance

Paid time off

Retirement plan

Vision insurance

Job summary

VA Boston Healthcare System in Boston, MA is seeking a Senior Data Scientist to build and deploy advanced AI capabilities for biomedical research and precision medicine. The on-site role focuses on turning complex clinical data into actionable insights using deep learning and production-grade ML systems.

The position emphasizes explainability, collaboration with clinical and scientific teams, and mentoring junior data scientists to advance organizational impact. Visa sponsorship is not indicated.

Qualifications

• US citizenship and ability to clear a US government background check.
• Degree in Mathematics, statistics, computer science, data science, or related field, at least bachelor's level.

Responsibilities

• Design, implement, and fine-tune state-of-the-art deep learning architectures for multi-omics integration and clinical data.
• Build scalable foundation models and generative AI systems for complex healthcare datasets.
• Apply ML methods for patient stratification, survival analysis, and disease progression modeling.
• Develop representation/self-supervised learning on temporal EHR data and other clinical signals.
• Create end-to-end pipelines handling missingness, high dimensionality, and batch effects.
• Use Explainable AI techniques like SHAP and Integrated Gradients for interpretable predictions.
• Build production-grade ML pipelines using distributed GPUs and cloud environments.
• Mentor junior data scientists and guide cross-functional teams.
• Draft technical docs, white papers, and contribute to publications.

Skills

Deep learning

Python

PyTorch

TensorFlow

Hugging Face

PyG/PyTorch Geometric

EHR data

OMOP

FHIR

Git

CI/CD

SQL

Distributed GPU computing

Explainable AI

Model monitoring

Education

Bachelor's degree in Mathematics/Statistics/CS/Data Science

Tools

PyTorch

TensorFlow

PyTorch Lightning

Hugging Face

PyG (PyTorch Geometric)

OMOP

FHIR

Python

Git

CI/CD

SQL

SHAP

Integrated Gradients

Job description

VA Boston Healthcare System is hiring a Senior Data Scientist to build and deploy advanced AI capabilities that support biomedical research and precision medicine. This onsite role in Boston, MA focuses on turning complex, multi-dimensional clinical data into actionable insights using deep learning, representation learning, and production-grade ML systems.

For this position, the salary range is USD 120,548 - 156,715 per year. The work spans exploratory analysis through model development and operationalization, with a strong emphasis on explainability and collaboration with clinical and scientific teams.

Responsibilities

• Design, implement, and fine-tune state-of-the-art deep learning architectures for multi-omics integration, including models such as Transformers, Graph Neural Networks, and Variational Autoencoders.
• Build scalable foundation models and generative AI systems for sparse, noisy, and high-dimensional clinical and healthcare datasets.
• Apply advanced machine learning methods for patient stratification, survival analysis, and disease progression modeling.
• Develop representation learning and self-supervised learning approaches to embed heterogeneous data streams, including temporal EHR data, continuous clinical monitoring, and structural biological data.
• Create end-to-end deep learning pipelines that handle missingness, extreme feature dimensionality, and batch-effect correction.
• Use Explainable AI techniques such as SHAP and Integrated Gradients to deliver biologically interpretable and clinically actionable predictions.
• Build, scale, and maintain production-grade AI/ML pipelines using distributed GPU computing and cloud environments.
• Implement best practices including model versioning, automated retraining, validation tracking, and continuous monitoring for data drift.
• Act as a data science and deep learning subject matter expert, guiding cross-functional teams of clinicians, biologists, and bioinformaticians.
• Mentor junior data scientists and machine learning engineers on advanced mathematical modeling and neural network architectures.
• Support scientific and organizational impact by drafting technical documentation, research white papers, and publishing findings in peer-reviewed journals.

Requirements

• US citizenship and ability to clear a US government background check.
• A degree in Mathematics, statistics, computer science, data science, or a directly related field, completed at least at the baccalaureate level in an appropriate major field of study.

Skills and Tools

Deep learning frameworks: PyTorch or TensorFlow, plus experience with high-level libraries such as PyTorch Lightning, Hugging Face, or PyG (PyTorch Geometric).

Clinical informatics: experience applying ML/DL to EHR data and working with clinical standards including OMOP and FHIR.

Software engineering: strong Python programming, with capabilities in Git, CI/CD, SQL, and related software engineering practices.

Technologies: Transformers, Graph Neural Networks, Variational Autoencoders, PyTorch, TensorFlow, PyTorch Lightning, Hugging Face, PyG, OMOP, FHIR, Python, Git, CI/CD, SQL, SHAP, Integrated Gradients, distributed GPU computing frameworks, and cloud environments.

Benefits

• Dental insurance
• Employee assistance program
• Flexible spending account
• Health insurance
• Health savings account
• Life insurance
• Paid time off
• Retirement plan
• Vision insurance

Reference: For qualification standards, see the OPM website: https://www.opm.gov/policy-data-oversight/classification-qualifications/general-schedule-qualification-standards/1500/data-science-series-1560/.