Postdoctoral Researcher: Causal ML for Healthcare Outcomes

University of Wisconsin-Madison; Madison (WI); Hybrid; USD 65,000 - 87,000; Full time

Job summary

University of Wisconsin-Madison seeks a Postdoctoral Research Associate to lead projects at the intersection of causal inference, machine learning, and clinical informatics in the ICU Data Science Lab. Hybrid work in Madison, WI is available, with 100% effort for 2-3 years, renewable annually.

The role involves benchmarking causal ML methods on RCT and observational data, leading manuscripts, and collaborating across centers while developing grant-writing skills.

Qualifications

• PhD in computer science, data science, statistics, biostatistics, epidemiology, or related quantitative field.
• Experience with causal inference methods (meta-learners, causal forests, doubly robust/ targeted estimators, propensity scores) and ML.
• Strong programming experience in Python and/or R.
• Proficiency with Git for version control.
• Strong written and oral communication skills.
• Ability to work independently and as part of a team.

Responsibilities

• Lead projects on causal ML for estimating individualized treatment effects (ITE) using EHR/RCT data.
• Benchmark multiple causal ML methods across trial characteristics and observational datasets.
• Lead manuscripts and pursue first-author opportunities; travel to clinical and AI conferences.
• Participate in multicenter collaborations and assist with grant writing best practices.
• Supervise UW graduate students and staff as needed; develop an individual development plan.

Skills

Causal inference methods

Machine learning

Written communication

Oral communication

Education

PhD in quantitative field

Tools

Python

R

Git

Job description

University of Wisconsin-Madison seeks a Postdoctoral Research Associate to lead projects at the intersection of causal inference, machine learning, and clinical informatics in the ICU Data Science Lab. Hybrid work in Madison, WI is available, with 100% effort for 2-3 years, renewable annually.

The role involves benchmarking causal ML methods on RCT and observational data, leading manuscripts, and collaborating across centers while developing grant-writing skills.