About Cedar:

Cedar is a healthcare billing and engagement platform that focuses on data science and consumer-centric design to improve the healthcare experience for patients. 

Project Title – Evaluation of AI-generated output for patient billing inquiries

Project Description:  

Cedar is building a ConversationalAI solution that includes LLM-generated responses to patient billing inquiries. This project is focused around designing and implementing an “LLM-as-a-judge” technique (within our tooling/tech stack) to effectively and robustly evaluate the LLM’s ability to explain complex billing scenarios to patients in human-friendly language.  

Knowledge, Skills, and Attributes required: 

• Experience working with Large Language Models and an understanding of best practices in areas such as prompt engineering, chaining, retrieval, vector search, evaluation of output
• Up to date with the latest advancements in generative AI and applying these advancements to ongoing projects
• Experience in Python and SQL

Competencies Preferred: 

• Has industry work experience in software/tech