Senior Data Scientist

About the role

Surescripts serves the nation through simpler, trusted health intelligence sharing, in order to increase patient safety, lower costs and ensure quality care. We deliver insights at critical points of care for better decisions — from streamlining prior authorizations to delivering comprehensive medication histories to facilitating messages between providers.

Responsibilities

• Data Exploration: Explore and preprocess data from various sources, measuring and ensuring data quality and integrity. Enrich data with external, auxiliary, or commercial data sets to enhance suitability for monetization or AI/ML.
• Advanced Analytics: Apply statistical and machine learning techniques to collect and analyze large datasets and identify patterns by developing predictive models, deep learning algorithms, and frameworks using tools like TensorFlow and PyTorch.
• Model Development: Design, build, and validate predictive models to solve business problems. Provide team leadership to ensure provenance and traceability in MLOps development cycles.
• Data Visualization: Create compelling visualizations to communicate findings and insights to stakeholders.
• Collaboration: Work closely with business leaders, product managers, data scientists, and engineers to translate business requirements into analytical solutions.
• AI-Assisted Planning & Design: Use AI assistants to accelerate requirements clarification, solution options, and technical design; convert outputs into reviewed artifacts (design docs, user stories, test plans).
• AI-Assisted Implementation: Use AI coding assistants to draft code/queries/notebooks/pipelines; perform human review for correctness, security, performance, and maintainability; follow IP/licensing and data-use policies.
• QA Oversight: Define acceptance criteria, test strategy, and validation methods (data checks; model metrics and bias/robustness as applicable); partner with engineering/QA on regression coverage and release readiness.
• AI-Teaming & Refinement: Iteratively refine solutions using prompt engineering, grounding/source practices, and evaluation rubrics; document prompts, assumptions, and decisions for repeatability.
• Mentorship: Provide guidance and mentorship to other data scientists, analysts and engineers within the team.

Qualifications

• Master’s degree in Mathematics, Computer Science, Statistics, or other related field; or equivalent experience
• 5+ years of experience in data science, data management and/or applying data analysis and reporting skills in a business context
• 5 years of experience with large healthcare transactional datasets/reporting
• 5 years of experience in healthcare transaction data, including QA, testing and reporting
• Expertise in programming languages to facilitate analysis (e.g. R, Python or MATLAB)
• Expertise with SQL /PLSQL, Relational and NoSQL databases, and Structured and Unstructured data
• Analytical background and research experience with large volumes of personal data
• Ability to translate statistical analysis into a written and verbal presentation for non-data science audience
• Experience in statistical modeling using healthcare data
• Knowledge of privacy laws and regulations around health data (HIPAA)
• Demonstrated proficiency using AI assistants across planning, design, implementation, and documentation (e.g., IDE/code assistants such as GitHub Copilot or Claude Code; chat-based assistants such as Microsoft Copilot; notebook/workbench assistants), with human review, traceability, and validation of AI-generated outputs.
• Demonstrated experience providing QA oversight for analytics/ML deliverables (defining acceptance criteria, designing validation approaches, partnering with engineering/QA on test automation and release readiness).
• Experience with AI-teaming techniques for refining technical solutions (prompt engineering, grounding/citation practices, evaluation rubrics and benchmarking, and documentation of AI-assisted decisions), including identifying and mitigating common failure modes (e.g., hallucinations, data leakage, insecure code).

Preferred Qualifications

• PhD degree in a quantitative field (e.g., Data Science, Statistics)
• Deep experience with large language models and/or natural language processing (e.g., fine-tuning, prompt/program orchestration, retrieval-augmented generation, or LLM evaluation frameworks)
• Familiarity with responsible AI practices (privacy, security, data handling, model risk considerations, and controls for AI-generated code/content) in regulated environments.
• Project management experience
• Google Cloud environment expertise
• Experience with MLOps frameworks such as GCP, DataBricks, or SnowFlake