AI Modeling and Federated Data Platforms SETA (#26-166)

• Provide internal subject matter expertise on federated and privacy-preserving AI for health data. Cover modeling developmental, health, communication, and functional trajectories across the lifespan. Also cover methods for finding outcome drivers that can be changed and targets that interventions can act on (ARPA-H).
• Give insight on whether proposed approaches are conceptually and technically sound:
• Federated architecture: federated learning and analytics across institutions and settings without moving raw data
• Privacy: privacy-enhancing technologies, such as differential privacy, secure multiparty computation, homomorphic encryption, and trusted execution environments
• Modeling: longitudinal and trajectory modeling, and finding subgroups of people with different trajectories
• Causal inference: telling modifiable drivers apart from correlations, including counterfactual methods and emulating target trials
• Multimodal data: combining TA1 data (genetic, ‘omics, environmental, clinical) with TA4 real-world data (sensor, audio, video, language, school-based measures)
• Trustworthiness: validation, generalizability, bias and fairness across age, sex, race and ethnicity, and support needs, plus interpretability and uncertainty
• Help set goals, expectations, and budgets for TA2 projects, including milestones for the platform, model performance, data onboarding, and interoperability.
• Help review and oversee funded TA2 projects. That includes integration across the program:
• bringing TA4 data streams into TA2 frameworks (ARPA-H)
• bringing in TA1 data
• providing model outputs that help TA3 choose and test interventions for each person

• Minimum five years of experience post-doc.
• Experience developing or evaluating machine learning and computational models with real-world health or biomedical data
• Experience with federated or distributed learning, or with other privacy-preserving computation on sensitive data
• Experience with longitudinal or causal modeling methods (e.g., trajectory or mixed-effects models, survival analysis, causal inference, causal ML)
• Experience with budgeting and program or project management

Experience/Expertise Preferred:

• Experience building or running multi-site research data networks (e.g., OHDSI, PCORnet, N3C, or federated genomics consortia)
• Data standards and interoperability (e.g., OMOP CDM, HL7 FHIR, GA4GH)
• Multimodal and foundation-model approaches for combining sensor, audio, video, language and ‘omics data
• Familiarity with health data governance and privacy requirements (HIPAA, and FERPA for school data), consent and assent for minors, and data use agreements
• Responsible AI frameworks and regulatory context (e.g., NIST AI RMF, FDA guidance on AI-enabled medical devices)
• Engineering for scalable platforms: cloud and high-performance computing, MLOps, security
• Autism or neurodevelopmental data and research
• Participatory or community data governance, i.e., giving autistic people and families a say in how their data and models are used
• Lived experience of autism is a plus. Disclosure is voluntary and not required.

Minimum Degree Requirement:

• PhD in computer science, machine learning, statistics or biostatistics, biomedical informatics, applied mathematics, electrical engineering, or a related field. A master’s degree with substantial relevant research or industry experience may be considered.