Data Scientist PennDnA

Description

Entity: Corporate Services

Department: PennDNA Data Science

Location: 3535 Market Street

Hours: M-F, 8:30am-5pm

About This Position

The Perelman School of Medicine is investing in AI-enabled workflow improvement, automation, and data-driven decision-making across its administrative and operational functions. This Senior Data Scientist will contribute to initiatives that apply data science and machine learning methods to organizational challenges — process analysis, operational modeling, and evaluation of AI tools such as large language models, retrieval-augmented generation, and vector databases for integration into existing systems.

Collaborators and Stakeholders

This position involves engagement with PSOM business units, IT and software engineering teams, data engineering groups, security and compliance partners, and the University of Pennsylvania Health System (UPHS) data science team. Work in this space also involves coordination with broader AI and data science efforts across Penn Medicine and the University

The Senior Data Scientist

The Senior Data Scientist will work closely with Machine Learning (ML) Engineers and be responsible for participating in the solving of complex problems from large sets of data, utilizing statistical analysis, machine learning, language models, and programming to develop solutions and drive innovation to address complex healthcare challenges. You will optimize research data tools and design scalable architecture to support our system clinical, operational and research efforts. The ideal candidate will have a strong background in data science and architecture, machine learning, statistical analysis and healthcare analytics, with experience in developing and deploying machine learning products to improve patient care and outcomes.

Accountabilities

• Predictive Analysis and Modeling: Build and validate algorithms to address complex healthcare problems. Develop proof-of-concept models and then iteratively improve the model. Design and utilize experimentation to quantify opportunity and outcomes. Maintain, implement and advance best practices as relevant for the data science discipline. Utilize advanced statistical methods and machine learning algorithms to extract deep insights from complex clinical, operational, and research datasets. Lead and execute moderately complex projects with minimal oversight. Serve as an expert in one or more sub-domains.
• Data Collection and Assessment: Work closely with administrators, clinicians, and informatics teams to evaluate existing data sources and identify potential gaps. Propose strategies for improving data integrity and collecting new data that minimize disruption to clinical workflows and operational processes.
• Collaboration: Collaborate with a multidisciplinary team, including ML engineers, site reliability engineers, vendors, clinicians, administrators, researchers, and others, to understand project requirements and develop solutions that meet organizational needs. Exhibit exceptional domain and data context awareness, stakeholder engagement, and ability to frame problems. This collaboration aims not only to advance healthcare technology but also to drive significant improvements in patient outcomes and operational efficiencies, demonstrating the tangible impact of our work. Provide subject matter expert review, guidance and consultation. Receive, triage, and refine requests from internal clients.
• Monitoring and Compliance: Actively monitor and evaluate the performance of analytical projects, ML models or research studies, to ensure they meet high standards of quality, effectiveness, and reliability. Maintain and optimize production models and applications. This role requires integrity and ethical use of data, adherence to legal and safety standards, and the proactive identification and mitigation of any form of drift or deviation from expected outcomes. This position requires a consistent commitment to maintaining the highest standards of operational and research integrity.
• Continuous Improvement: Demonstrate a commitment to continuous learning and professional development. Stay current with industry trends, best practices, and emerging technologies in data architecture, database development, machine learning, statistical analysis and healthcare analytics. Look for opportunities to optimize the team’s processes and workflows.
• Performs duties in accordance with Penn Medicine and entity values, policies, and procedures
• Other duties as assigned to support the unit, department, entity, and health system organization

Minimum Requirements

Required Education and Experience

• Bachelor's Degree Computer Science, Statistics, Data Science, Mathematics or related field is required (Master’s Degree is preferred).
• 4+ years of Experience in data architecture, database development, machine learning, statistical analysis and healthcare analytics. Proven track record of leading and executing moderately complex projects with minimal oversight.

Required Skills and Abilities

• Subject Matter Expertise –Expert in machine learning techniques deep learning, natural language processing (NLP), and predictive modeling. Expertise in relational databases (e.g., SQL Server, Oracle), data modeling, and database administration. Proficiency in programming languages commonly used in data science, such as Python or R, and experience with machine learning libraries/frameworks (e.g., TensorFlow, PyTorch, scikit-learn). Proficiency in research data collection platforms, such as REDCap, and electronic health record (EHR) systems. Strong understanding of stakeholder needs. Apply knowledge to solve problems and contribute ideas to team strategy.
• Analytical thinking – Strong critical thinking and problem-solving skills with keen attention to detail.
• Communication & Interpersonal Skills- Excellent verbal and written communication skills. Ability to communicate complex concepts to a diversity of stakeholders.
• Relationship building - Develop credibility and trust. Collaborative. Ability to develop and maintain professional and collegial relationships. Mentor more junior members of the team.
• Innovation - Apply creative approaches to problem solving and develops solutions to address issues. Flexible. Eager to learn new skills and technologies. 
• Healthcare Knowledge- Knowledge of healthcare data, regulations, compliance requirements, and data privacy standards.

The Data Scientist

The Data Scientist will apply machine learning and statistical techniques to clinical, administrative, biological, and wearable device data to create immense value for patients and health systems. These methods will be used to study clinical practices and implement policies and interventions related to disease screening, population health, and decision science. Individuals in this role are expected to be comfortable working as a software engineer, a quantitative researcher, and a collaborative member of a clinically oriented research team.

Accountabilities

• Work closely with members of a large research team to identify and answer important healthcare questions with appropriate statistical techniques
• Lead large data acquisition, data mining, Natural Language Processing (NLP), and analysis projects; data types and sources will vary, but will certainly include clinical data
• Create and manage protocols for the analysis of data collected through the course of usual clinical care, mobile technologies, and by other passive means
• Design and execute research projects utilizing advanced computational techniques to generate novel medical insights and to build clinical decision support systems
• Communicate findings to researchers, clinicians, and administrators
• Drive the collection of new data and the refinement of existing data sources
• Work closely with a team of developers and researchers to conduct scholarly work at the intersection of serious illness and clinical informatics
• Performs duties in accordance with Penn Medicine and entity values, policies, and procedures
• Other duties as assigned to support the unit, department, entity, and health system organization

Minimum Requirements

Required Education and Experience

• Bachelor's Degree a relevant technical field, e.g. statistics, mathematics, physics, computer science And 3+ years in a relevant role
• Or
• Master's Degree a relevant technical field, e.g. statistics, mathematics, physics, computer science And 2+ years in a relevant role
• Experience solving analytical problems using quantitative approaches

Required Skills and Abilities

• Fluency with statistical and machine learning techniques such as decision trees, feed-forward and recurrent neural networks, graphical models, clustering, and dimension reduction
• Experience manipulating and analyzing complex, large volume, high-dimensionality data from varying sources
• Fluency in coding in R and/or Python (Python)
• Familiarity with reproducible scientific workflows (e.g. Jupyter notebooks or Rmarkdown) and version control (e.g. git)
• A strong passion for empirical research and for answering hard questions with data
• A flexible analytic approach that allows for results at varying levels of precision
• Ability to communicate complex quantitative analysis in a clear, precise, and actionable manner
• Familiarity with relational databases and SQL
• Fluency in NoSql design, deployment and analyzing on many TB’s of data preferred

We are an Equal Opportunity employer. Candidates are considered for employment without regard to race, ethnicity, color, sex, sexual orientation, gender identity, religion, national origin, ancestry, age, disability, marital status, familial status, genetic information, domestic or sexual violence victim status, citizenship status, military status, status as a protected veteran or any other status protected by applicable law.