Senior Data Scientist - Clinical AI

CVS Health•New York, NY

4d•$101,970 - $203,940

About The Position

CVS Health's Analytics & Behavior Change (A&BC) team is focused on solving complex problems at the intersection of technology and healthcare. The team utilizes advanced analytics, clinical informatics, and hypothesis-driven methods to transform data into actionable, customer-centric insights that drive growth, improve health outcomes, and expand healthcare access across CVS Health businesses. The A&BC organization is expanding its Clinical Data Science & AI team to leverage clinical data and analytics for a transformational shift in consumer healthcare leadership in the U.S. As a Senior Data Scientist - Clinical AI, your role involves activating CVS Health's clinical data repository to enhance outcomes across various business lines and use cases. You will act as a liaison between clinical data assets and consumers (analysts, data scientists, business partners), ensuring data accessibility, proper documentation, fitness for purpose, and adherence to clinical and regulatory standards.

Requirements

4+ years of experience in data science, machine learning, or applied NLP with significant experience in healthcare or a similarly regulated domain, and a proven track record of delivering production-grade work.
Deep, hands-on experience in NLP, including building and deploying NLP systems end-to-end, understanding tradeoffs, and making principled architecture decisions across text preprocessing, NER, classification, and topic modeling.
Proven experience designing and deploying LLM/SLM-based systems, including prompt engineering, fine-tuning, RAG architecture, evaluation frameworks, or deploying language models in production.
Strong foundation in traditional machine learning, including supervised and unsupervised methods, feature engineering, model selection, cross-validation, and performance evaluation.
Proficiency in best coding practices, including the use of version control, writing maintainable code, and ensuring reproducible code bases.
Advanced EDA skills to systematically explore datasets, identify data quality issues, surface insights, and make informed decisions before modeling.
Expert-level Python (pandas, scikit-learn, PyTorch or TensorFlow, Hugging Face Transformers) and SQL for working with large-scale healthcare datasets, writing performant, maintainable code.
Experience with cloud-based data and ML platforms, preferably Google Cloud Platform (GCP) — BigQuery, Vertex AI, or equivalent.
Excellent presentation and communication skills, with the ability to clearly explain technical work and its business implications.
Strong judgment and common sense, including knowing when an LLM is the appropriate tool and the ability to manage deadlines and guide junior team members.
Genuine curiosity and a desire to learn, including reading papers, trying new tools, and a focus on delivering results.

Nice To Haves

Significant experience working with clinical text data such as clinical notes, discharge summaries, or pathology reports.
Working knowledge of clinical coding systems and terminologies (ICD-10, SNOMED-CT, LOINC, RxNorm, CPT, NDC, UMLS) and their relevance to NLP pipelines.
Hands-on experience with clinical data standards (HL7, FHIR, CCD/C-CDA) and common data models (e.g., OMOP).
Experience building or contributing to clinical NLP pipelines, including entity extraction, relation extraction, negation detection, or section segmentation from clinical narratives.
Deep understanding of model evaluation in clinical contexts, including sensitivity/specificity tradeoffs, clinical validation, and responsible AI practices in healthcare.
Understanding and experience guiding MLOps practices such as model versioning, experiment tracking, CI/CD for ML, and model monitoring.
Experience working directly with clinical stakeholders (physicians, nurses, clinical operation teams) and tailoring presentations and findings to different audience levels.
Privacy, security, and compliance experience, including HIPAA/HITRUST, de-identification/tokenization, and PHI/PII handling.
Master's degree or higher in Health Informatics, Biomedical Informatics, Clinical Informatics, Public Health, Epidemiology, Data Science or a related field.
A clinical background (RN, PharmD, MD, or similar) with a transition into data science or AI.

Responsibilities

Extract signal from unstructured clinical text using NLP and language model techniques on clinical notes, CCD documents, and other free-text clinical data to generate structured, actionable features for downstream analytics and predictive models.
Build and fine-tune Small Language Models (SLMs) tailored to clinical use cases, balancing performance, cost, latency, and compliance.
Leverage large language models (LLMs) where they provide clear value (e.g., training data creation, entity extraction, zero-shot classification), while also knowing when traditional ML, rules-based, or simpler statistical methods are more appropriate.
Develop and validate predictive models using both classical ML (gradient boosting, logistic regression, survival analysis) and modern deep learning approaches to support clinical decision-making and population health initiatives.
Conduct rigorous Exploratory Data Analysis (EDA) on structured and unstructured clinical datasets to uncover patterns, assess data quality, identify feature candidates, and inform modeling strategy.
Communicate methodology, results, and recommendations clearly to technical and non-technical stakeholders through visualizations, notebooks, and presentations, translating complex AI/ML concepts into actionable language.
Collaborate with machine learning engineers, data engineers, clinical informaticists, and business partners to ensure clinical data pipelines support AI/ML workflows and that model outputs are integrated into products and decision-making processes.
Continuously evaluate emerging techniques in NLP, foundation models, and clinical AI, bringing new ideas to the team, prototyping rapidly, and advocating for evidence-based approaches.
Ensure all work complies with HIPAA, data privacy regulations, and internal data stewardship policies, particularly when handling PHI and unstructured clinical text.