Data Scientist II - Quantitative Biology, Multi-OMICs Integration, and AI/ML Modeling

About the role

Performs research, analysis, and modeling on organizational data and data sets utilizing advanced statistical methods to mine and analyze complex and unstructured data sets. Offers complex analysis and utilizes advanced algorithms and statistical software. Adheres to all protocols.

The Pulmonary, Allergy, Critical Care, and Sleep Medicine Division comprises approximately 70 clinical staff and over 100 research staff working across locations such as Bridgeside Point, Biomedical Science Tower (BST), and UPMC hospitals (Presbyterian, Shadyside, East, Jameson, Mercy). The division delivers inpatient services at five hospitals and over 70,000 outpatient visits annually, with a research mission focused on lung, microbiome, COVID‑19, sleep medicine, and allergy and immunology. The Benam Lab at the University of Pittsburgh Departments of Medicine and Bioengineering seeks a Data Scientist II to provide advanced analytical and computational expertise for a multidisciplinary program on human‑relevant experimental systems (microphysiological systems; Organs‑on‑Chips). The role will lead development and implementation of data analysis pipelines, statistical modeling frameworks, and machine learning approaches to integrate and interpret complex biological datasets, support high‑dimensional analysis across virology, imaging, and multi‑OMICs platforms, and contribute to standardized, regulatory‑aligned data frameworks for predictive modeling and translational decision‑making.

Responsibilities

• Design and implement robust, scalable data analysis pipelines for multimodal datasets, including virology, imaging, and multi-OMICs data
• Lead development and application of statistical models to quantify infection dynamics and therapeutic response endpoints
• Develop and apply machine learning and AI‑based approaches for pattern recognition, predictive modeling, and target discovery
• Perform integrative, systems‑level analyses across diverse data types (molecular, cellular, functional, and temporal datasets)
• Collaborate with investigators on study design, statistical planning, and development of quantitative frameworks for experimental studies
• Establish and maintain reproducible computational workflows, including data preprocessing, quality control, and version‑controlled pipelines
• Develop data standards, organization strategies, and reporting structures aligned with regulatory expectations (e.g., ISTAND‑ready frameworks)