Data Scientist - Clinical Machine Learning & Flow Cytometry

St. Jude Children's Research Hospital•Memphis, TN

About The Position

At St. Jude Children's Research Hospital, we are committed to accelerating discoveries that improve outcomes for children with catastrophic diseases through innovation, collaboration, and scientific excellence. The Data Scientist, Clinical Machine Learning and Flow Cytometry, will play a critical role in advancing next-generation diagnostic analytics by developing and implementing machine learning solutions for high-dimensional spectral flow cytometry data. Working closely with clinical faculty, laboratory scientists, and multidisciplinary data science teams, this position will help transform measurable residual disease (MRD) detection and clinical flow cytometry interpretation through scalable, reproducible, and clinically validated analytical approaches. The successful candidate will contribute to improving diagnostic accuracy, reducing turnaround times, enhancing laboratory efficiency, and strengthening St. Jude's leadership in precision diagnostics, translational research, and the responsible application of artificial intelligence in healthcare. The Data Scientist will lead the development, validation, and deployment of machine learning solutions for high-dimensional clinical flow cytometry data. Working in close collaboration with faculty and laboratory leadership in Clinical Immunopathology, the incumbent will design and implement analytical frameworks that support automated identification of rare and clinically relevant cell populations, improve measurable residual disease (MRD) detection, reduce manual interpretation burden, and enhance diagnostic accuracy and reproducibility. The position will support the development of machine learning pipelines for spectral flow cytometry datasets, longitudinal quality monitoring systems, and scalable analytical workflows for clinical laboratory operations.

Requirements

Bachelor's degree with 10+ years of relevant post-degree work experience in relevant area (e.g., bioinformatics, cheminformatics, statistics/computer science with a background in biological sciences or chemistry) OR Master's degree with 8+ years of relevant experience OR PhD with 5+ years of relevant experience.
Substantial experience in at least one programming or scripting language and at least one statistical package, with R preferred.
Python (required), including pandas, NumPy, SciPy, Scikit-learn, PyTorch, TensorFlow, XGBoost, and LightGBM.
R and Bioconductor ecosystem.
Flow cytometry data analysis tools and standards, including FCS file formats, FlowCore, FlowJo integration, Cytobank, Spectre, FlowSOM, UMAP, and t-SNE.
Statistical modeling, hypothesis testing, longitudinal analysis, and statistical process control.
Machine learning model development, validation, deployment, and monitoring.
Data visualization using Plotly, Dash, Streamlit, Shiny, Tableau, or comparable technologies.
SQL and NoSQL databases.
Cloud and high-performance computing environments.
Git-based version control and software development best practices.
Experience with MLOps, reproducible research workflows, and containerization technologies, including Docker and Singularity.
Familiarity with healthcare data, laboratory information systems, and clinical validation practices.

Nice To Haves

Experience applying machine learning to biomedical, clinical, translational, or laboratory datasets.
Experience with high-dimensional single-cell or flow cytometry data.
Experience developing and validating analytical methods in regulated or clinical laboratory environments.
Demonstrated record of scientific publication and interdisciplinary collaboration.
Experience translating research algorithms into operational workflows that improve efficiency, quality, or patient care.

Responsibilities

Lead data analysis and deliver high-quality results by formulating advanced and innovative machine learning approaches to address challenging clinical flow cytometry analysis questions.
Adapt and optimize analytical methodologies to support high-dimensional spectral cytometry and MRD detection initiatives.
Design, develop, validate, and maintain machine learning pipelines for supervised and unsupervised analysis of flow cytometry data, including clustering, dimensionality reduction, classification, anomaly detection, and predictive modeling.
Deliver data products, analytical reports, visualizations, and technical documentation that support clinical implementation, regulatory review, and scientific publication.
Document analytical methods, model performance, validation results, and quality assurance procedures.
Establish and document protocols, best practices, and reproducible workflows for machine learning applications in clinical flow cytometry and laboratory quality monitoring.
Develop methods for longitudinal monitoring of assay performance, including statistical process control, drift detection, and quality assessment of instrument, reagent, and workflow variability.
Recommend opportunities to automate and improve existing analytical workflows and implement enhancements that increase throughput, reproducibility, and operational efficiency.
Evaluate, benchmark, and test emerging machine learning methods, algorithms, and technologies applicable to biomedical and clinical diagnostics.
Develop reusable code, workflows, and software tools that can be leveraged across projects and laboratories.
Collaborate with pathologists, laboratory scientists, bioinformaticians, statisticians, and data scientists to translate clinical and scientific questions into computational solutions.
Participate in manuscript preparation, scientific presentations, abstracts, and dissemination of project outcomes to internal and external research communities.
Lead and participate in interdisciplinary projects involving data science, laboratory medicine, clinical diagnostics, and translational research.
Act as project manager when required.