Senior Data Scientist jobs in Chicago, IL

Tell me about a predictive model you built on clinical or claims data that made it into production.

What they are checking: Whether they have carried healthcare models past the notebook into something people actually use.

How would you predict risk of readmission using EMR data, and what pitfalls would you watch for?

What they are checking: Whether they understand leakage, coding changes and missingness patterns that make healthcare models look better than they are.

How have you used NLP or large language models on clinical notes or other unstructured healthcare text?

What they are checking: Whether they can apply modern language models to messy clinical text and evaluate them honestly.

How do you check a model for bias across patient groups like race, payer type or age?

What they are checking: Whether they treat fairness as a measured property of the model, which matters when outputs affect patient care.

You're combining claims data with EMR data from different hospitals. How do you handle the differences in coding and completeness?

What they are checking: Whether they can reconcile disparate healthcare sources without quietly introducing errors into the analysis.

A clinical stakeholder doesn't trust your model's output. How do you build their confidence?

What they are checking: Whether they can explain models in clinical terms and invite scrutiny rather than defend a black box.

Walk me through how you'd decide between a simple statistical model and a complex machine learning model for a client question.

What they are checking: Whether they choose methods by what the problem and audience need rather than what is most impressive.

Tell me about a time you partnered with engineering to make a data science solution scalable.

What they are checking: Whether they can work across product and engineering to turn prototypes into production-ready capabilities.