
Data Scientist
Posted 7 hours ago

Posted 7 hours ago
This is a fully remote position, open to applicants in United States.
• Develop predictive and prescriptive machine learning models for pharmacy cost and risk, encompassing feature engineering, model selection, and analysis of explainability.
• Create risk and comorbidity scoring at the member level utilizing drug identifiers linked to clinical conditions and severity weights.
• Implement machine learning techniques to streamline clinical operations processes, such as automating prior-authorization overrides.
• Examine unstructured member and clinical text through methods like sentiment analysis, topic modeling, and tokenization.
• Leverage large language models (LLMs), copilots, and internal AI services to enhance the automation of clinical policy and documentation workflows.
• Assess AI models, define evaluation datasets, and establish checks for drift and validation.
• Design and uphold probabilistic fuzzy matching systems to reconcile member identifiers across various platforms.
• Track match rates, analyze false positives and fragmentation, and maintain documentation of data lineage.
• Generate clinical and pharmacy analytics, focusing on medication adherence and persistence metrics.
• Conduct quality assurance and validate reporting products, pharmacy trend dashboards, and per-member-per-month (PMPM) metrics.
• Create analytical tools and prototypes featuring lightweight front ends, such as Streamlit.
• Provide validated datasets and tables to the data warehouse, facilitating the transition to production.
• Audit claims files and verify model outcomes prior to their release.
• Document models, logic, data sources, schedules, and troubleshooting procedures.
• Collaborate with stakeholders from clinical, reporting, pricing, client success, and engineering teams.
• Complete the Aptive Index Assessment.
• Hold a degree in a quantitative discipline (data science, statistics, computer science, applied mathematics) or possess equivalent experience.
• Have 2–3 years of experience utilizing Python and SQL for data analysis, machine learning, natural language processing, data quality, and record-matching solutions.
• Exhibit strong Python skills for data science and machine learning (e.g., familiarity with pandas and a modeling stack) and demonstrate proficiency in SQL.
• Show proven experience in building and validating machine learning models, including tasks such as feature engineering and model explainability.
• Have experience with natural language processing techniques (e.g., sentiment analysis, topic modeling) and applying AI/LLM tools to practical workflows, including validation of outputs.
• Possess experience in entity resolution, probabilistic record matching, and data quality analysis.
• Be comfortable working with modern cloud data warehouses and data lakes, collaborating with data engineering teams for production hand-off.
• Have experience in healthcare, pharmacy benefit management (PBM), or claims data.
• Be familiar with pharmacy data concepts (e.g., NDC, GPI, ATC, formulary tiers, prior authorization, rebates).
• Have experience with compliance-driven reporting (e.g., URAC / PQA measures).
• Demonstrate experience in building analytical front ends or dashboards (e.g., Streamlit, business intelligence tools) for non-technical audiences.
• Be willing and able to travel (10%-20%).
• Opportunity to influence industry changes within the pharmacy benefits management sector while ensuring the best possible patient outcomes.
• Work in an environment where individuals flourish, as the success of our team translates to the prosperity of our business.
• Competitive salary package that includes health, dental, vision, and other benefits.
• Flexible remote work options.
• Commitment to equal employment opportunities.
Commit
Counterpart
Oportun
Get handpicked remote jobs straight to your inbox weekly.