CS-Research Assistant

CS-Research Assistant

The School of Nursing is seeking a data science-focused student research worker to support AI and machine learning research in cardiovascular health informatics. The position involves working with both structured and unstructured electronic health records (EHR) data, applying advanced computational methods including machine learning and natural language processing under the direction of Dr. Kang's federally funded research program.

Responsibilities will include assisting with:

• Preparing, cleaning, and organizing research datasets (e.g., structured EHR data such as vital signs, lab values, medications, and diagnoses)
• Supporting data quality checks and basic data summaries under supervision
• Assisting with extracting and organizing information from clinical notes using existing tools/workflows, as directed by the research team
• Supporting literature reviews and background research related to AI/ML and clinical research
• Assisting with documentation related to data management and research protocols (e.g., data dictionaries, IRB/DUA materials), as assigned
• Participating in research team meetings and providing updates on assigned tasks
• Performing other duties as assigned This is a grant funded position. Continued employment is based on availability of funding.

Minimum Qualifications

• Bachelors degree or equivalent in education and experience
• Strong programming skills in Python and/or R
• Experience with machine learning libraries (scikit-learn, TensorFlow, PyTorch, or similar)
• Familiarity with NLP techniques and tools (spaCy, NLTK, Hugging Face, or similar)
• Knowledge of statistical analysis and data visualization
• Experience working with large datasets and database management
• Strong analytical and problem-solving skills
• Excellent attention to detail and organizational abilities
• Ability to work independently and collaboratively in a research team
• Strong written and verbal communication skills

Preferred Qualifications

• Experience working with electronic health records or clinical data • Familiarity with healthcare terminologies (SNOMED-CT, ICD, LOINC) • Knowledge of HIPAA and research data security requirements • Experience with deep learning approaches for clinical NLP

Equal Opportunity Employer / Disability / Veteran

Columbia University is committed to the hiring of qualified local residents.