Mindoula Health is hiring an early-career Healthcare Data Scientist to play a critical role in building our analytics capabilities. You will provide data-driven insights from a wide range of healthcare data, support program performance measurement, and ensure analytic outputs are reliable.

What You'll Do

Process and analyze structured and unstructured healthcare data, including claims, assessments, surveys, chat/call logs, and third-party sources.
Maintain and improve data pipelines and modeling code for scalability, automation, and reproducibility.
Investigate data issues and contribute to improvements in data quality and integrity.
Collaborate with team members to conduct analyses and modeling workflows with guidance from senior staff.
Execute and validate outputs from production notebooks and pipelines, flagging inconsistencies and escalating unusual findings.
Apply statistical methods—including propensity score matching, difference-in-differences, and time series modeling—to evaluate program impact and calculate ROI.
Perform ad-hoc and root cause analyses to uncover trends and support findings from evaluations.
Partner with the data science team to define scopes, participate in code reviews, and support ad-hoc analysis requests.
Work cross-functionally with data engineering, analytics, and software teams on shared initiatives.
Help maintain and update technical documentation and training materials.
Prepare clear and accurate reports for internal use and client deliverables.
Translate complex analytical findings into accessible insights for business and clinical stakeholders.

What We're Looking For

A Master’s degree in a quantitative field such as epidemiology, psychology, health administration, public health, computer science, statistics, data science, economics, mathematics, or engineering. A bachelor’s degree with 4+ additional years of equivalent experience will also be considered.
2-6 years of experience (internship, specific coursework, and projects apply).
Experience with health-related data is required (e.g., claims, program data, EHR).
Statistics coursework and/or training is required; familiarity with core statistical concepts including variance, relative risk, incidence/prevalence.
Strong foundation in programming languages including SQL, Python, and R.
Familiarity with programming notebooks (e.g., Jupyter, Databricks) and tools like Pandas or NumPy.
Experience writing SQL to query relational databases (e.g., Athena, PostgreSQL, MS Access).
Proven ability to troubleshoot code, technical issues, and uncover root cause data issues.
Strong attention to detail—able to spot inconsistencies or incorrect values in output.
Excellent communication and interpersonal skills, with the ability to explain complex concepts to non-technical stakeholders.
Enthusiasm for working in a collaborative, cross-functional team environment, paired with a proactive, problem-solving mindset.
Comfort with working in a virtual, remote environment and leveraging virtual communication platforms.