NCCT/CTMC NLP/LLM Analyst

Pay Range

Overview

The National Center for Clinical Trials (NCCT) is designed to serve as an innovative platform to revolutionize and catalyze the conduct of clinical trials−greatly accelerating the translation of scientific findings into improvements in the prevention, diagnosis, and treatment of disease for our communities and patients. The NCCT will offer core services for patient recruitment and enrollment, trial administration and follow-up, and to gather real world data and evidence.

The Clinical Trial Methods Center (CTMC) has been established within the Wake Forest University School of Medicine to provide the necessary tools and expertise that the NCCT will access and apply to deliver many of its core services.

This position will be housed within the Center for Artificial Intelligence Research and will support the Real-World Advocate DAta for Research (RADAR) team within the CTMC. RADAR focuses on the development of real-world electronic health record (EHR) longitudinal datasets, registries, the incorporation of external data, and contribution to active cohort development.

Key Responsibilities

1. Design and implement predictive models using AI/ML techniques on structured and unstructured data real-world data (e.g., EHRs, radiology reports, clinical notes, images).

2. Conduct comprehensive data preprocessing, feature engineering, and model validation.

3. Collaborate with clinicians and researchers to frame problems, understand data needs, and interpret model outputs.

4. Evaluate model accuracy, fairness, bias, and explainability.

5. Translate insights into operational recommendations through dashboards, briefings, and stakeholder presentations.

6. Writes the results section of reports.

7. Develops and implements new innovative procedures in the areas of data collection, quality control, presentation of results, and statistical analyses.

Qualifications

· Master's in Data Science, Computer Science, Biomedical Informatics, Statistics, Engineering, or a related field.

· Minimum of three years’ experience in Data Science, Computer Science, Biomedical Informatics, Statistics, Engineering, or a related field.

· Demonstrated experience with machine learning, natural language processing (NLP), Large Language Models (LLM), or AI model development.

· Proficiency in Python, R, and data manipulation libraries (e.g., pandas, scikit-learn, TensorFlow/PyTorch).

· Experience working with electronic health record or administrative claims datasets preferred.

· Excellent communication skills and ability to translate complex technical findings for non-technical stakeholders.

Helpful Experience and Knowledge Areas

· Prior involvement in healthcare, academic operations, or industry analytics.

· Familiarity with EHR systems (Epic, Cerner, etc.) and/or EHR Common Data Models (OMOP, PCORnet, etc.)

Our Commitment to You:

Advocate Health offers a comprehensive suite of Total Rewards: benefits and well-being programs, competitive compensation, generous retirement offerings, programs that invest in your career development and so much more – so you can live fully at and away from work, including:

Compensation

• Base compensation listed within the listed pay range based on factors such as qualifications, skills, relevant experience, and/or training
• Premium pay such as shift, on call, and more based on a teammate's job
• Incentive pay for select positions
• Opportunity for annual increases based on performance

Benefits and more

• Paid Time Off programs
• Health and welfare benefits such as medical, dental, vision, life, and Short- and Long-Term Disability
• Flexible Spending Accounts for eligible health care and dependent care expenses
• Family benefits such as adoption assistance and paid parental leave
• Defined contribution retirement plans with employer match and other financial wellness programs
• Educational Assistance Program