We are seeking a Sr. Data Scientist. The Sr. Data Scientist will serve as a data science subject matter expert and lead the design, development, and execution of data science initiatives requiring advanced machine learning and production-level code. The Sr. Data Scientist will research and implement state-of-the-art modeling methodologies, pipelines and ML lifecycle architecture to support projects and downstream decision making. The Sr. Data Scientist will lead digital tool development efforts and conduct analytics to support full use of data procured by the Brady Urological Institute. The Sr. Data Scientist will foster collaboration efforts with data visualization specialists, data engineers, data scientists, analysts, researchers, program managers, coaches, and other external collaborators and partners in support of a portfolio of data projects.

In this role, the Sr. Data Scientist will serve as the lead computational scientist for the Cancer Ecology Center within the Brady Urological Institute, owning the design, development, and production engineering of the Center's machine-learning and simulation models. The Sr. Data Scientist will write and maintain the core modeling codebase - including next-generation development of the ExposoGraph exposome knowledge-graph platform and the build-out of the Cancer Ecology Digital Twin (CEDT), a predictive simulation environment for modeling tumor-ecosystem dynamics and individualized disease trajectories. The Sr. Data Scientist will leverage Python skills across four broad domains: classic ML (regression/classification tasks; e.g., XGBoost/LightGBM), deep learning (neural networks/ODEs; e.g., PyTorch), state-of-the-art transformer/diffusion methodologies, and causal inference (double machine learning, ATE/CATE; e.g., CausalML), as well as utilize MLOps practices such as Git versioning and CICD pipelines. These skills will facilitate translating complex, multi-modal biomedical and environmental datasets into validated, reproducible models that inform research and clinical decision-making. The successful candidate will combine deep analytical modeling and machine-learning expertise with strong software-engineering discipline, the ability to architect data and modeling pipelines from the ground up, and a track record of leading technically rigorous projects from concept to production. Experience bridging research and applied environments, fluency in complex, interpretable, and causal machine-learning methods, and the capacity to collaborate across data engineers, visualization specialists, clinicians, and research scientists are essential.

Specific Duties & Responsibilities

• Design data modeling processes to build statistical and simulation models on complex data sets.
• Provide detail-oriented and organized analytics and models to transform data sets into meaningful insights to inform stakeholder decision making.
• Research best practices and state-of-the-art methodologies that can be applied in the assigned area.
• Lead the identification of data sets for modeling which leads to quantitative conclusions.
• Clean, assess quality and bias, explore, analyze, and visualize data; may delegate duties as necessary.
• Document, share, and train others on methods; may delegate duties as necessary.
• Function as a subject matter expert and/or project lead.
• Share in-depth knowledge as a resource.
• Train data analysts on the use of software tools to carry out analysis. Update training on a regular basis.
• Develop models and tools related to the use of data. Provide input into other models and tools.
• Lead cross functional teams that may include developers, analysts, data scientists, researchers, policy experts, external partners, contractors, and vendors.
• Communicate with leadership, as well as technical and non-technical stakeholders.
• Other duties as assigned.

Minimum Qualifications

• Master's Degree.
• Seven years of related experience.
• Additional education may substitute for required experience and additional related experience may substitute for required education beyond a high school diploma/graduation equivalent, to the extent permitted by the JHU equivalency formula.

Preferred Qualifications

• PhD.

Technical Skills & Expected Level of Proficiency

• Data Tools and Platforms - Authority
• Data Tool and Resource Development - Authority
• Data Visualization - Authority
• Machine Learning - Authority
• Project Management - Authority
• Programming Languages - Advanced
• Statistical Modeling - Authority
• Version Control System - Advanced

The core technical skills listed are most essential; additional technical skills may be required based on specific division or department needs.

Classified Title: Sr. Data Scientist
Role/Level/Range: ATP/04/PI
Starting Salary Range: $135,900 - $238,400 Annually ($150,000 targeted; Commensurate w/exp.)
Employee group: Full Time
Schedule: M-F; 8:30am - 5:00pm
FLSA Status: Exempt
Location: Remote Optional
Department name: Urology
Personnel area: School of Medicine