"Postdoc Research Fellow"

The successful candidate will build and optimize a cloud-native lakehouse integrating structured, unstructured, and streaming healthcare data using Spark, Trino, MinIO, and SQL/NoSQL systems, while incorporating ML and LLMs for natural-language queries, predictive analytics, and advanced reasoning in healthcare and oncology.

Postdoc Research Fellow is expected to coordinate and support students in the development and execution of research tasks and to support faculty investigators, senior researchers, and laboratory personnel supporting the principal investigator in the development and execution of research, data collection and analysis through computational and analytical methods, writing and publishing of scientific papers in peer-reviewed journals, and through the identification and submission of applications for extramural funding.

• Design and optimize scalable database schemas, SQL/NoSQL queries, and distributed lakehouse platforms (Spark, Trino, MinIO, Delta/Iceberg).
• Develop intelligent pipelines for data ingestion, transformation, and real-time analytics across structured, unstructured, and streaming healthcare data.
• Integrate AI/ML and LLMs for query optimization, indexing, predictive analytics, and advanced reasoning.
• Apply knowledge intelligence (e.g., knowledge graphs, embeddings) to support advanced analytics and decision-making.
• Monitor and tune performance, identifying bottlenecks and implementing continuous improvements.
• Ensure HIPAA-compliant security, integrity, and governance of cloud-native data systems.
• Collaborate with clinicians, scientists, and engineers to translate healthcare needs into data-driven solutions.

Responsibilities Include:

• Execute research activities under the guidance and supervision of the center directors
• Support, assist, and coordinate student and lab personnel activities associated with project execution when required
• Proposal preparation and identification of funding sources
• Project documentation and reports

Requirements Include:

• Ph.D. in Computer Science, Data Science, or related field with a strong record of peer-reviewed publications.
• Expertise in large-scale SQL/NoSQL databases and cloud-native big data systems (Spark, Trino, Databricks, Delta/Iceberg, MinIO).
• Strong background in SQL development, query optimization, indexing, and performance tuning.
• Experience with AI/ML and LLM integration for database optimization, analytics, and decision support.
• Familiarity with streaming architectures and data pipelines.
• Knowledge of HIPAA, PHI/PII compliance, and secure data governance in healthcare contexts.
• Proficiency in programming (Python, Scala, R, or Java) and container/orchestration tools (Docker, Kubernetes).