Research Data Analyst 2 (Hybrid Opportunity)

SLAC; Palo Alto (CA); Hybrid; USD 90,000 - 130,000; Full time

Job summary

Stanford University’s Division of Computational Medicine is seeking a Research Data Analyst 2 to reveal how rare diseases emerge in patients’ medical histories. You will work with Stanford patient data to identify cohorts and reconstruct diagnostic journeys across multiple diseases, integrating notes, diagnoses, procedures, medications, and lab results.

Proficiency in Python and SQL is expected, with collaboration across faculty and clinicians.

Responsibilities

• Develop and evaluate methods to identify rare-disease cohorts using structured EHR data and clinical text.
• Build reproducible pipelines that organize clinical events into patient diagnostic timelines.
• Create annotation and review tools to help clinicians validate extracted information and guide improvements.
• Investigate data-quality issues and extraction errors, using clinical feedback to refine computational methods.
• Develop performance metrics and automated tests for timeline extraction and downstream disease-risk models.
• Translate analyses into clear datasets, figures, reports, presentations, and manuscript contributions.
• Document methods, validation results, and limitations so findings are understandable and reproducible.
• Collaborate with clinical and technical colleagues to shape methods, interpret results, and advance the research.

Job description

Stanford’s Division of Computational Medicine brings together expertise in biomedical informatics, data science, and medicine to tackle complex questions about human health. We develop computational and statistical methods that help researchers make sense of health data and generate evidence for clinical and translational research.

We are seeking a Research Data Analyst 2 to help reveal how rare diseases emerge in patients’ medical histories. Working with electronic health records from Stanford patients with confirmed diagnoses, you will develop methods to identify patient cohorts and reconstruct diagnostic journeys across 10 rare diseases. Your work will connect information from clinical notes, diagnoses, procedures, medications, and laboratory results to support research on disease recognition and risk modeling.

In this role, you will contribute throughout the research process, from translating clinical questions into computational methods to evaluating results and sharing findings in publications and presentations. You will write Python and SQL code, build tools that bring clinical expertise into method development, and work closely with faculty, clinicians, and technical researchers. This is an opportunity to apply your programming and analytical skills to clinically meaningful questions while deepening your experience in biomedical data science.

Primary Responsibilities:

• Develop and evaluate methods to identify rare-disease cohorts using structured EHR data and clinical text.
• Build reproducible pipelines that organize clinical events into patient diagnostic timelines.
• Create annotation and review tools that help clinicians validate extracted information and guide improvements.
• Investigate data-quality issues and extraction errors, using clinical feedback to refine computational methods.
• Develop performance metrics and automated tests for timeline extraction and downstream disease-risk models.
• Translate analyses into clear datasets, figures, reports, presentations, and manuscript contributions.
• Document methods, validation results, and limitations so research findings can be understood and reproduced.
• Collaborate with clinical and technical colleagues to shape methods, interpret results, and advance the research.

This position offers a hybrid schedule, with onsite work three days per week, subject to operational needs.