Design and implement AI/ML models to derive insights from complex, high-dimensional datasets (e.g., EHRs, genomic data, imaging, and biosensor outputs).
Collaborate with multidisciplinary teams (clinicians, epidemiologists, data engineers, policy analysts) to define research questions and develop data-driven solutions.
Apply and tailor machine learning techniques to solve domain-specific problems in:
Predictive modeling (e.g., risk stratification for TBI, PTSD, chronic illness)
Time-series analysis (e.g., vital sign monitoring, disease progression)
Natural language processing (NLP) (e.g., extraction from clinical notes, case reports)
Computer vision (e.g., radiology and pathology image classification)
Unsupervised learning (e.g., clustering phenotypes or patient cohorts)
Causal inference and counterfactual modeling for treatment effect estimation
Federated learning and privacy-preserving AI for multi-site collaboration
Support model validation, bias detection, and ethical AI practices in compliance with health data privacy regulations (HIPAA, 21 CFR Part 11).
Contribute to the development of dashboards, decision support tools, and research publications.
Participate in proposal development for research funding from DHA, MTEC, NIH, VA, and other agencies.
Master’s or Ph.D. in Computer Science, Data Science, Biomedical Informatics, Statistics, or related discipline.
3+ years of experience applying AI/ML in healthcare, biomedical research, or public health.
Proficiency in Python, R, and ML frameworks such as TensorFlow, PyTorch, Scikit-learn, XGBoost.
Deep understanding of ML concepts: supervised and unsupervised learning, deep learning, ensemble methods, and model evaluation techniques.
Experience working with health data: EHR, claims, registries, or clinical trial datasets.
Familiarity with healthcare interoperability standards and terminologies (e.g., HL7 FHIR, SNOMED CT, LOINC).
Prior experience supporting DoD, VA, HHS, or federally funded R&D programs.
Hands-on experience with NLP libraries (e.g., spaCy, Hugging Face Transformers) and medical imaging tools (e.g., MONAI, OpenCV).
Understanding of algorithmic fairness, health equity analysis, and SDOH integration.
Experience with cloud-based data platforms and ML pipelines (e.g., AWS, Azure, Databricks, Snowflake).
McKesson
JobGo
Intuition Machines
SIXT
Intermedia Cloud Communications