Job Description
This position will support computational oncology and cancer informatics
research initiatives focused on transforming complex clinical data into
structured, actionable datasets for research, quality improvement, clinical
trial identification, and care delivery optimization. The role will emphasize
applied machine learning, natural language processing, and large language
model-driven workflows using real-world clinical data, including electronic
health record data, pathology reports, radiology reports, clinical notes,
genomics, treatment data, and other institutional data sources.
The Data Scientist will work semi-independently in close collaboration with
clinical investigators, informatics teams, biostatisticians, and other data
science stakeholders to design, build, evaluate, and refine computational
pipelines. The ideal candidate will have practical prior experience developing
data science workflows in Python and using modern machine learning or LLM-based
tools in real projects.
Job Responsibility
Develop, test, and maintain Python-based data pipelines for clinical
research, quality improvement, and computational oncology projects.
Support cancer informatics projects involving natural language processing,
machine learning, large language models, and structured extraction from
unstructured clinical data.
Build workflows for processing clinical notes, pathology reports, radiology
reports, treatment records, genomics reports, and other real-world healthcare
data sources.
Implement and evaluate LLM-assisted workflows, including prompt engineering,
structured output generation, model benchmarking, validation pipelines, and
error analysis.
Assist with the development of retrieval-augmented generation workflows,
vector search, embedding-based retrieval, and related approaches where
appropriate.
Work with clinical subject matter experts to translate oncology-focused
research questions into executable data science tasks.
Perform data cleaning, data wrangling, exploratory analysis, feature
engineering, model development, and model performance evaluation.
Generate reproducible analyses, reports, dashboards, tables, and
visualizations to communicate findings to clinical and operational
stakeholders.
Maintain clear documentation of code, analytic decisions, model assumptions,
validation methods, and project outputs.
Participate in model validation efforts, including comparison of
computational outputs against clinician-reviewed reference standards.
Contribute to manuscript, abstract, grant, and presentation development
through data analysis, figure generation, and methods documentation.
Work independently on assigned analytic tasks while communicating progress,
limitations, and blockers clearly to project leadership.
Job Qualification
Bachelor’s Degree in Computer Science, Informatics, Statistics, Engineering,
Data Science, or related field, required. Master’s Degree, preferred.
Minimum of two (2) years of post-graduate training or experience involving
quantitative data analysis, required and working with clinical data, data
science, and machine learning, preferred.
Working familiarity with basic medical and health information technology
concepts, including standardized terminologies and ontologies and electronic
health records, as well as Data Warehousing and Business Intelligence tools,
required.
Expertise in working with SQL relational databases and statistical or general
programming languages (e.g., Python, R), required.
Deep understanding of statistical and predictive modeling concepts,
machine-learning approaches, clustering and classification techniques, and
recommendation and optimization algorithms.
HIGHLY PREFERRED
Demonstrated prior experience building or implementing applied data science,
machine learning, NLP, or LLM-based workflows. Completion of a short AI
certificate, bootcamp, or introductory course alone is not sufficient for
this role.
Strong practical experience with Python for data science, including pandas,
NumPy, scikit-learn, Jupyter notebooks, and reproducible analytic workflows.
Prior experience applying machine learning, natural language processing, or
large language models to real-world data problems.
Experience using off-the-shelf LLMs through APIs or enterprise platforms,
including structured prompting, output parsing, evaluation, and workflow
integration.
Experience with retrieval-augmented generation, vector databases, embeddings,
semantic search, or document retrieval pipelines.
Experience working with clinical, biomedical, or electronic health record
data.
Familiarity with oncology data, cancer registries, pathology reports,
radiology reports, genomics reports, or clinical trial data.
Experience working in secure data environments, enterprise data warehouses,
Databricks, Spark, SQL databases, or cloud-based analytic platforms.
Ability to write clean, maintainable, well-documented code and use version
control such as Git.
Demonstrated ability to work semi-independently, manage multiple analytic
tasks, and communicate technical concepts to non-technical clinical
collaborators.
Prior experience contributing to academic research, abstracts, manuscripts,
grant-funded projects, or healthcare quality improvement initiatives.
Understanding of model evaluation concepts including accuracy, precision,
recall, F1 score, calibration, error analysis, and external validation.
Experience with prompt engineering alone is not sufficient; candidates should
have substantive prior experience in data science, machine learning,
computational research, or applied analytics.
Additional Salary Detail
The salary range and/or hourly rate listed is a good faith determination of
potential base compensation that may be offered to a successful applicant for
this position at the time of this job advertisement and may be modified in the
future. When determining a team member's base salary and/or rate, several
factors may be considered as applicable (e.g., location, specialty, service
line, years of relevant experience, education, credentials, negotiated
contracts, budget and internal equity).