Data Scientist - Clinical AI
Core
Activating CVS Health's clinical data repository to improve outcomes across multiple lines of business by extracting signals from unstructured clinical text and building predictive analytics solutions.
Role type
Senior IC clinical data scientist (NLP & LLMs)
Builds
Domain-specific Small Language Models (SLMs), predictive models, and structured features for downstream analytics and clinical decision-making.
Domain
Healthcare / Clinical Informatics / AI
Deliverable
production ML models
Required skills
NLP (text preprocessing, NER, classification), LLM/SLM fine-tuning and deployment, traditional ML (gradient boosting, survival analysis), Python (pandas, scikit-learn, PyTorch/TensorFlow, Hugging Face), SQL, cloud ML platforms (GCP), EDA, data governance (HIPAA)
Preferred skills
Clinical coding systems (ICD-10, SNOMED-CT, etc.), clinical data standards (HL7, FHIR, OMOP), MLOps, clinical stakeholder collaboration
Technologies
Python, SQL, GCP (BigQuery, Vertex AI), PyTorch, TensorFlow, Hugging Face Transformers, Git
Responsibilities
Extract signal from unstructured clinical text using NLP and language models; Build and fine-tune domain-specific Small Language Models (SLMs); Develop predictive analytics solutions using classical ML and deep learning; Conduct rigorous Exploratory Data Analysis (EDA) on clinical datasets; Communicate findings and methodology to technical and non-technical stakeholders; Collaborate with ML engineers, data engineers, and clinical informaticists to integrate model outputs into products.
Seniority
Senior, hands-on IC