Staff Software Engineer / Machine Learning Engineer - Radiology

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

About The Position

We are seeking a highly motivated and experienced Machine Learning Engineer to develop advanced machine learning (ML), deep learning (DL), and foundational AI models for medical imaging. This role focuses on building robust algorithms for segmentation, quantification, and detection across CT, MRI, and X-ray. This position sits at the center of a well-resourced, data-rich research environment with established infrastructure for multi-institutional data aggregation, curation, and large-scale annotation. St. Jude Children’s Hospital has incredible high-performance computing resources. The lab leverages curated datasets from diverse sources, dedicated annotation teams, and external engineering support, enabling this role to focus on high-impact model development, validation, and clinical translation. Many projects are designed with a path toward regulatory clearance via FDA’s 510(k) or De Novo pathways, and the successful candidate will work closely with regulatory and quality experts to support reproducible, well-documented, and clinically deployable AI solutions. This role offers a unique combination of academic productivity (authorship opportunities) and real-world impact through translation into clinical practice.

Requirements

Bachelor's degree in computer science, data science, information science, business, or related field.
Minimum Requirement: Bachelor's degree with 5+ years of experience required.
Experience Exception: Master's degree with 3+ years of experience.
Experience with programming languages, databases, and software development lifecycle
Experience with the position-specific technical stack preferred
Experience with the position-specific scientific domain preferred
Proven performance in earlier role/comparable role

Nice To Haves

Master's degree preferred.
3+ years of experience developing ML/DL models for image analysis
Demonstrated experience with segmentation, detection, and/or quantitative imaging algorithms (2D and/or 3D)
Strong proficiency in Python and deep learning frameworks (e.g., PyTorch , TensorFlow)
Experience with modern architectures (U-Net variants, detection frameworks, transformers, or foundational models)
Familiarity with DICOM and medical imaging workflows
Strong understanding of evaluation metrics (Dice, IoU , ROC/AUC, sensitivity/specificity)
Experience with version control and collaborative development (e.g., Git)
Demonstrated ability to produce clear, structured technical documentation
Experience using modern LLM-based coding assistants (e.g., Claude, Codex, or similar) to enhance development workflows (Strongly preferred)
Experience developing and documenting AI solutions for clinical translation or regulatory submission (e.g., FDA 510(k))
Familiarity with Good Machine Learning Practice (GMLP)
Experience collaborating with regulatory, quality, or cybersecurity teams
Exposure to software security principles (e.g., secure coding, vulnerability assessment, penetration testing concepts)
Experience with large, multi-institutional datasets
Familiarity with radiology workflows and quantitative imaging biomarkers
Experience with cloud or high-performance computing environments
Experience deploying models into research or clinical environments

Responsibilities

Develop, train, and validate state-of-the-art ML/DL models for segmentation, quantification, and detection across CT, MRI, and X-ray
Design and implement 2D and 3D model architectures (CNNs, transformer-based, and foundational models)
Build scalable pipelines for data preprocessing, model training, evaluation, and deployment
Develop quantitative imaging methods (e.g., volumetrics, density measurements, biomarker extraction)
Leverage curated, multi-institutional datasets to ensure model generalizability and robustness
Collaborate with radiologists and engineering teams to define clinically meaningful outputs
Produce regulatory-grade documentation for datasets, model development, validation, and performance
Ensure reproducibility and traceability of experiments (data, model, and code versioning)
Work collaboratively with regulatory and quality experts to support FDA 510(k) and De Novo submissions, including providing technical documentation and validation evidence
Contribute to software quality and security practices, including supporting activities such as vulnerability assessment and penetration testing in collaboration with cybersecurity and regulatory teams
Utilize modern AI-assisted development tools (e.g., LLM-based coding agents) to accelerate development and improve code quality
Participate in team-based development practices (code reviews, Git, testing frameworks)
Support manuscripts, grants, and technical reporting