Data Scientist

Data Scientist – AI & Real-World Evidence Based at Schneider Children’s Medical Center Why This Role Matters Children are not small adults, yet much of the medicine they receive was never designed or tested with them in mind. Drugs, medical devices, and increasingly AI-based tools reach the market and the clinic after being developed and validated almost entirely on adult data, and children are left to benefit from them, or be harmed by them, without the evidence to know which. We want to change that reality. This role exists to build the evidence that children deserve: rigorous, real-world, and grounded in data from children themselves. About the Role We are seeking a Data Scientist to lead work at the intersection of artificial intelligence, multimodal clinical data, and real-world evidence, as part of a team working to heal today’s children and create tomorrow’s healthy adults. This is a hands-on role at a leading children’s hospital, combining advanced modeling, rigorous research methods, and close collaboration with clinicians, researchers, and industry partners. The role has two connected missions. The first is to lead real-world evidence studies in collaboration with pharmaceutical, medical device, and technology companies, including multimodal studies and the evaluation of AI-based medical devices in real clinical settings. The second is to evaluate data platforms and technologies for organizing, integrating, and analyzing multimodal clinical data for research. Both missions share a single goal: to determine, rigorously and independently, what AI and real-world data can actually deliver for children’s health. Requirements The role is intended for candidates with a master’s degree or PhD in data science, computer science, biostatistics, or another relevant quantitative field, with proven experience leading applied research or AI projects in healthcare, from the initial question through to deliverables. We are looking for strong hands-on experience developing and validating machine learning models on medical data, including deep learning, along with high proficiency in Python and SQL. Experience working with large clinical databases and longitudinal data is required, including data processing, integration, quality control, and handling missing data, as is experience working with more than one data modality. Candidates should bring a solid grounding in statistics and observational study design, including an understanding of bias and confounding, and the ability to critically evaluate AI systems and data products rather than take their outputs at face value. We expect well-documented, reproducible work, the ability to quickly learn new clinical domains and translate clinical and research needs into a work plan, and strong scientific and critical thinking, independence, initiative, teamwork, and excellent English. Above all, we are looking for someone who can move forward even when the need is not yet well defined: asking the right questions, understanding the possibilities and limitations of data and technology, and choosing the right research approach. Significant Advantages Significant advantage will be given to experience in the pharmaceutical, medical device, or digital health industry, or at a CRO, or in leading studies in collaboration with such companies. Additional advantages include experience with the regulatory and evidence requirements for AI-based medical devices; experience in RWE, pharmacoepidemiology, and causal inference, including matching and weighting methods; experience with large language models, foundation models, or multimodal model architectures; experience evaluating clinical data platforms or data technologies; and familiarity with medical data standards and terminologies such as OMOP, FHIR, ICD, and ATC.