Graduate Research Assistant, Quantitative and Systems Health Services

Jobtailor; Austin (TX); On-site; USD 28,000 - 42,000; Full time

Job summary

Jobtailor in Austin, TX, invites PhD candidates to join the Translational AI Excellence and Application in Medicine (TEAM-AI) Lab under Dr. Hongfang Liu.

The role focuses on fine-tuning LLMs for biomedical data normalization, developing data standards, and building knowledge graphs for disease areas. You'll design data-preprocessing pipelines for longitudinal EHRs, implement predictive models, document work, and prepare manuscripts for conferences.

Qualifications

• Enrolled in a Ph.D. program at UT Austin in a quantitative field.
• Ph.D. students or advanced Master's students transitioning to doctoral studies.
• PhD must have been received within the last three years.
• Proficiency in Python and core libraries (NumPy, Pandas, Scikit-Learn, PyTorch/TensorFlow).
• Coursework or experience in ML, DL, NLP, or probabilistic graphical models.
• Strong background in linear algebra, calculus, probability, statistics.
• Excellent written and oral communication; rigorous code documentation.
• Resume/CV and letter of interest required; eligible to work in the U.S.
• Criminal background check may be required for finalists.

Responsibilities

• Fine-tune and evaluate LLMs and Transformer models for biomedical data.
• Map observational healthcare data to standards and build knowledge graphs.
• Develop data-preprocessing, feature engineering, and imputation pipelines for EHR data.
• Implement and benchmark predictive modeling algorithms in the clinical domain.
• Maintain open-source code and write technical documentation.
• Prepare manuscripts for conference submission.
• Contribute to active grants under supervision of Dr. Hongfang Liu and colleagues.
• Work in the TEAM-AI Lab translating AI innovations in biomedicine.

Skills

Python Programming

Machine Learning

Deep Learning

Natural Language Processing

Data Normalization

Written Communication

Oral Communication

Collaborative Development

Education

Ph.D. student at UT Austin

Advanced Master’s student transitioning to PhD

PhD completed within last 3 years

Tools

NumPy

Pandas

Scikit-Learn

PyTorch

TensorFlow

Job description

• Fine-tune, prompt-engineer, and evaluate open-source Large Language Models (LLMs) and Transformer architectures for biomedical data normalization
• Map observational healthcare data to data standards and assist in constructing common data elements and knowledge graphs for disease areas
• Develop data-preprocessing, feature-engineering, and missing-data imputation pipelines for longitudinal EHR records, time-series vitals, and diagnostic imaging features
• Implement and benchmark baseline machine learning algorithms for predictive modeling tasks in the clinical domain
• Maintain open-source code repositories and write technical documentation
• Prepare manuscripts for conference submission
• Contribute to active research grants under the supervision of Dr. Hongfang Liu and lab faculty members
• Work in the Translational AI Excellence and Application in Medicine (TEAM-AI) Lab on translating AI innovations in biomedicine and healthcare

Requirements

• Enrolled in a Ph.D. program at The University of Texas at Austin in Computer Science, Biomedical Informatics, Data Science, Electrical & Computer Engineering, or a related quantitative field
• Ph.D. students or advanced Master's students transitioning to doctoral studies
• PhD must have been received within the last three years
• Proficiency in Python and core computational libraries including NumPy, Pandas, Scikit-Learn, and PyTorch/TensorFlow
• Coursework or experience in machine learning, deep learning, natural language processing, or probabilistic graphical models
• Solid background in linear algebra, multivariable calculus, probability theory, and statistical inference
• Written and oral communication skills
• Track record of rigorous code documentation and collaborative software development
• Relevant education and experience may be substituted as appropriate
• Resume/CV and letter of interest required
• Must be eligible to work in the United States and complete federal Employment Eligibility Verification (I-9) if hired
• Criminal history background check required for finalists

Core Competencies

Demonstrates expertise in fine-tuning and evaluating Large Language Models and Transformer architectures for biomedical applications, alongside proficiency in Python and machine learning frameworks. Strong capabilities in data preprocessing, feature engineering, and collaborative software development are essential.

Highest-signal resume keywords

• Python Programming
• Machine Learning
• Deep Learning
• Natural Language Processing
• Data Normalization

ATS Optimization Keywords

Hard Skills

• Large Language Models
• Transformer Architectures
• Data Preprocessing
• Feature Engineering
• Missing-Data Imputation
• Predictive Modeling
• Statistical Inference
• Linear Algebra
• Multivariable Calculus
• Probabilistic Graphical Models

Soft Skills

• Written Communication
• Oral Communication
• Collaborative Development

Industry Keywords

• Biomedical Informatics
• Translational AI
• Healthcare Data
• EHR Records
• Knowledge Graphs

Tools & Technologies

• NumPy
• Pandas
• Scikit-Learn
• PyTorch
• TensorFlow