Temporary Intern - Data Scientist

Overview

We are looking for a curious, driven Data Science intern to join our analytics team for the summer. You will work on real healthcare data problems alongside full-time data scientists and engineers — not internal demos — touching everything from data wrangling and feature engineering to model evaluation and lightweight deployment.

 

This is not a passive internship. Healthcare is a domain where accuracy, compliance, and explainability matter, and you will help shape how predictive and analytical models inform decisions for payers and providers. Expect to ship something you are proud of by the end of the summer.

Responsibilities

 

Depending on your strengths and team needs, you will contribute to one or more of the following areas:

 

 

• Predictive modeling and feature engineering

◦ Build and evaluate classification or regression models using Python and standard ML libraries

◦ Engineer features from claims, clinical, or operational datasets

◦ Measure model performance using AUC, log-loss, calibration, and other appropriate metrics

 

• Data analysis and quality

◦ Clean, transform, and profile datasets; document data-quality findings and assumptions

◦ Write SQL against relational databases to extract and shape analytical inputs

◦ Communicate findings through clear visualizations and written summaries

 

• Model deployment and reproducibility

◦ Build lightweight APIs or endpoints to surface model outputs (e.g., FastAPI)

◦ Contribute to version-controlled, reproducible workflows using Git

◦ Document pipelines so teammates can extend and audit your work

 

• Applied research support (stretch opportunity)

◦ Assist with experiments at the intersection of ML and healthcare workflows

◦ Explore approaches such as adaptive fine-tuning or evaluation harnesses for LLM-based components

 

• Complete all responsibilities as outlined in the annual performance review and/or goal setting. 
• Complete all special projects and other duties as assigned. 
• Must be able to perform duties with or without reasonable accommodation. 

 

This job description is intended to describe the general nature and level of work being performed and is not to be construed as an exhaustive list of responsibilities, duties and skills required. This job description does not constitute an employment agreement and is subject to change as the needs of Cotiviti and requirements of the job change. 

Qualifications

 

• Education: currently pursuing a Bachelor’s or Master’s degree in Data Science, Statistics, Computer Science, or a related quantitative field

• Programming: hands-on experience with Python for data analysis — pandas, scikit-learn, matplotlib

• Core ML: solid understanding of classification, regression, train/test discipline, and model evaluation

• SQL: comfort writing queries against relational databases

• Project ownership: experience taking a project end-to-end — question, data, model, insight — through coursework, personal projects, or prior internships

• Communication: ability to explain technical work clearly to non-technical stakeholders

 

Nice to have:

 

• Exposure to model deployment using REST APIs, FastAPI, or similar

• Familiarity with Git and basic experiment tracking

• Experience with R, XGBoost, or other gradient-boosting libraries

• Interest in healthcare data, payer/provider workflows, or regulated environments

• Exposure to LLMs, fine-tuning techniques (e.g., LoRA), or evaluation methods

 

What you’ll gain:

 

• Hands-on experience building production-oriented data science work, not just demos

• Exposure to real-world challenges in healthcare analytics — accuracy, compliance, explainability

• Mentorship from experienced data scientists and engineers on a dedicated summer project

• A defined deliverable and end-of-term demo to your team and broader stakeholders

• Cohort programming, cross-functional networking, and competitive intern compensation

 

Cognitive/Mental Requirements:

• Communicating with others to exchange information.
• Problem-solving and thinking critically.
• Completing tasks independently.
• Interpreting data.
• Making timely decisions in the context of a workflow.
• Maintaining focus.
• Assessing the accuracy, neatness and thoroughness of the work assigned.
• Learning new tasks and completing ta