Data Scientist

## Overview **Being on medication is tough enough.** **We want to make getting it the easy part**. Getting prescriptions to patients has become increasingly complex. When things get messy along the prescription journey, pharmaceutical manufacturers rely on us to untangle the process and create a clear path—allowing patients to build trusting relationships with their medication brands. We’re not only committed to taking the pain out of the prescription process, but we’re also devoted to bringing the brightest minds together under one roof. We bring together diverse voices—engineers, pharmacists, customer service veterans, developers, program strategists and more—all with one vision. Each perspective and experience makes ConnectiveRx better than the sum of its parts. The Data Scientist position will perform data analysis as well as research, design, simulate, and prototype new algorithmic product designs based on business needs, with a focus on optimizing the speed, impact and cost of financial assistance delivered to the patient while minimizing risk of fraud or abuse of benefits. ## Responsibilities - Develop and deploy supervised machine learning models, which utilize data provided by the company’s call centers and live programs, and unsupervised machine learning models on Amazon Web Services; - Gain insight into and munge data sets for use in modeling; - Collaborate with customers to brainstorm hypotheses, leverage unique data sets, conduct trial analyses and share results at key milestones; - Align design efforts with ConnectiveRx services, data sets and value proposition; - Visualize data in the Looker dashboard, tuning ML Models; and - Work closely with different clients for identifying anomaly patterns in data. - Hybrid Work Schedule. - Standard company benefits. ## Qualifications - Master’s degree or foreign equivalent in Business Analytics and Project Management, Information Technology, or a closely related field; - Experience with/demonstrated knowledge of developing robust AI tool for automated detection and overseeing its design, implementation, and refinement to ensure reliable performance; - Experience with/demonstrated knowledge of processing and managing image data for model training and evaluation; - Experience with/demonstrated knowledge of Machine Learning; - Experience with/demonstrated knowledge of integrating AI models with a website using REST API in Python, designing and implementing API endpoints to facilitate seamless interaction between the model and the web-based application; - Experience with/demonstrated knowledge of designing scalable APIs and structured data models to support efficient data processing and inference requests; - Experience with/demonstrated knowledge of leveraging Google Cloud for scalable model deployment, enabling efficient storage, computation, and inference in a cloud-based environment; - Experience with/demonstrated knowledge of collaborating within an Agile Scrum framework, contributing to iterative development, cross-functional collaboration, and continuous improvement of the AI-driven solution; - Experience with/demonstrated knowledge of improving data accessibility for non-technical staff; - Experience with/demonstrated knowledge of creating SQL scripts for simplified querying; - Experience with/demonstrated knowledge of data cleaning; - Experience with/demonstrated knowledge of implementing JDBC for seamless database connectivity and integrated REST-based services within the Serenity framework; - Experience with/demonstrated knowledge of maintaining version control using Git; - Experience with/demonstrated knowledge of developing and executing automated integration testing in Serenity; - Experience with/demonstrated knowledge of validating application functionality and ensuring software reliability; - Experience with/demonstrated knowledge of designing data models, sequence diagrams, and class diagrams; and - Experience with/demonstrated knowledge of using: REST-based se…