Data Scientist

Job Title: Data Scientist - RAG architecture Duration: 12+ Months (Possible temp to hire) Location: Arden Hills, MN 55112 Hybrid Role Responsibilities: • Responsible for the initiation, design, development, execution, and implementation of data science research projects. • Receives minimal technical direction/review on broad scope or complex projects. • Viewed as an expert in one or more technologies. • Investigates the feasibility of applying scientific principles and concepts to potential technologies, processes and products. • Plans and executes research to prove feasibility of concepts. • Build analytics tools that utilize the data pipeline to provide actionable insights into customer acquisition, operational efficiency and other key business performance metrics. • Work with stakeholders throughout the organization to identify opportunities for leveraging company data to drive business solutions. • Mine and analyze data from company databases to drive optimization and improvement of product development, clinical marketing techniques and business strategies. • Assess the effectiveness and accuracy of new data sources and data gathering techniques. • Develop custom data models and algorithms to apply to data sets. • Use predictive modeling to increase and optimize customer experiences, revenue generation, ad targeting, and other business outcomes. • Coordinate with different functional teams to implement models and monitor outcomes. • Develop processes and tools to monitor and analyze model performance and data accuracy. • Work with stakeholders including the Executive, Product, Data and Design teams to assist with data-related technical issues and support their data infrastructure needs. • Keep our data separated and secure across national boundaries through multiple data centers and AWS regions. • Create data tools for analytics and data scientist team members that assist them in building and optimizing our product into an innovative industry leader. • Work with data and analytics experts to strive for greater functionality in our data systems. Education/Experience: • 9+ Years with BS, 6+Years with MS. • Expertise with Python, SQL, Vector Databases technologies in AWS /Azure • First, real production Retrieval-Augmented Generation (RAG) and Large Language Model (LLM) engineering, not Jupyter Notebook work: someone who has shipped and operated these systems and has opinions on retrieval quality, orchestration, cost, and observability. • Second, evaluation rigor in messy, high-cardinality classification where labels overlap heavily and output feed regulatory workflows, which means thinking in SME agreement and error analysis rather than holdout accuracy. • Third, the ability to work fluently across clinical SMEs, Quality, and IT/Security, translating feedback into architecture and communicating tradeoffs honestly, because in post-market surveillance, over-claiming is a real risk. we can also help provide them guidance when they start, but their experience with evaluation of Rag architecture will be key.