Senior Manager RWE Biostats

At Bristol Myers Squibb, our employees often ask, “Who are you working for?”—a question that fuels collaboration, accountability, and urgency in our work. Our purpose-driven culture inspires us to discover, develop, and deliver innovative medicines to prevail over serious diseases. We offer uniquely interesting and meaningful work, opportunities for growth, and a supportive environment that values inclusion, wellbeing, flexibility, and comprehensive benefits. This is work that transforms the lives of patients, and the careers of those who do it.

Position Summary

You will join a cutting-edge Drug Development Data Science and Advanced Analytics (DSAA) team to advance the global drug development process. We are looking for a candidate with strong computational, statistical, and data engineering capabilities and a demonstrated track record of working with real-world data (RWD) , including electronic health records (EHR), claims data, patient registries, and other real-world evidence (RWE) sources, to generate actionable insights that inform clinical trial design and treatment evaluation . This role requires deep expertise across the full RWD analytics lifecycle: from data sourcing, engineering, and quality assessment, through to statistical analysis, summary extraction, and AI/ML predictive modeling.

In addition to the RWD focus, this role contributes to broader data science objectives spanning genomics, proteomics, imaging, flow cytometry, and other biomarker data types generated from clinical trials. As a hands-on individual contributor, you will drive exploratory and confirmatory analyses that support drug development decisions across early-to-late phase programs, collaborating closely with Biostatistics leads, Translational and Clinical Scientists, and cross-functional partners. We are looking for a hands-on, state-of-the-art practitioner.

What You'll Do

Real-World Data Science (Deep Expertise)

• •Data Engineering & Infrastructure
• •Design, build, and maintain scalable data pipelines for ingesting, harmonizing, and transforming large-scale RWD sources, including EHR, medical/pharmacy claims, patient registries, lab data, and linked multi-source datasets
• •Develop and implement robust data quality frameworks to assess completeness, consistency, accuracy, and fitness-for-purpose of RWD sources for specific analytical questions
• •Apply data standardization and interoperability best practices (e.g., OMOP CDM, FHIR, SNOMED, ICD, RxNorm) to enable cross-source analyses and longitudinal patient cohort construction
• •Build reproducible, well-documented, version-controlled codebases using Python, R, SQL, and cloud platforms (e.g., AWS, Azure, Databricks)

• •Data Processing, Curation & Cohort Development
• •Define and implement rigorous patient identification, cohort selection, and exposure/outcome definition algorithms from complex, noisy real-world datasets
• •Develop and apply algorithms for data cleaning, deduplication, record linkage, and handling of missing, irregular, or censored data in RWD contexts
• •Extract clinically meaningful features and summary measures from unstructured and structured RWD, including NLP-based extraction from clinical notes and free-text fields
• •Construct longitudinal patient-level datasets that accurately capture treatment patterns, disease progression, healthcare utilization, and outcomes

Oncology Real-World Data (Emphasis Area)

• •Work with oncology-specific RWD sources including EHR platforms (e.g., Flatiron Health, Tempus), tumor registries (e.g., SEER, NCDB), and molecularly-linked datasets integrating clinical outcomes with genomic profiling (e.g., NGS, TMB, MSI, PD-L1)
• •Construct and validate oncology patient cohorts, including LOT sequences, biomarker-defined subgroups (e.g., PD-L1, MSI, TMB, EGFR, KRAS), and longitudinal treatment histories from fragmented, incomplete real-world records
• •Apply methods appropriate for oncology RWD outcomes (rwOS, rwPFS, TTNT, rwRR) while addressing oncology-specific analytical challenges, including immortal time bias, informative censoring, death ascertainment, and treatment switching
• •Support comparative effectiveness and external control arm (ECA) analyses for oncology programs, with awareness of FDA/EMA guidance on RWE use in oncology regulatory submissions
• •Bring familiarity with immuno-oncology treatment landscapes and associated analytical complexities, including delayed response patterns and immune-related adverse events (irAEs)

• •Statistical Analysis & Real-World Evidence Generation
• •Apply advanced statistical and epidemiological methods appropriate for RWD, including propensity score methods (matching, weighting, stratification), instrumental variable analysis, difference-in-differences, interrupted time series, and other causal inference frameworks
• •Perform robust characterization of patient populations, treatment patterns, comparative effectiveness, and outcomes from RWD to support clinical development strategy
• •Develop and apply survival analysis and time-to-event models to evaluate treatment effects and disease trajectories in real-world cohorts
• •Apply longitudinal and mixed-effects modeling approaches to repeated-measures RWD with appropriate handling of informative censoring and irregular observation times
• •Contribute to the design and execution of RWE studies, observational analyses, and external control arm (ECA) analyses to inform regulatory submissions and clinical decisions

• •AI/ML Predictive Modeling & Insight Generation
• •Develop, validate, and deploy AI/ML predictive models using RWD to support patient stratification, treatment response prediction, disease progression modeling, and identification of novel prognostic and predictive factors
• •Apply classical machine learning (e.g., regularized regression, gradient boosting, random forests) and deep learning approaches (e.g., recurrent/transformer architectures for longitudinal EHR data) with rigorous model evaluation and explainability practices
• •Leverage NLP and large language model (LLM)-based approaches for structured and unstructured RWD extraction, phenotyping, and evidence synthesis
• •Apply causal ML frameworks to estimate treatment effects and inform counterfactual analyses from observational RWD
• •Implement strong evaluation standards: nested cross-validation, calibration assessment, out-of-sample validation, and transparent reporting of model performance and limitations

• •Clinical Trial Design & Drug Development Informatics
• •Leverage RWD analytics to characterize natural history of disease, estimate baseline event rates, and define estimands to inform clinical trial design, including feasibility assessments, site selection, and patient enrichment strategies
• •Support development of external control arms (ECAs) and synthetic control analyses using RWD in collaboration with Biostatistics and Regulatory Affairs
• •Contribute analytical insights to inform go/no-go decisions, dose selection, endpoint selection, and inclusion/exclusion criteria for clinical trials
• •Partner with lead and protocol statisticians in contributing to statistical analysis plans (SAPs) for RWD/RWE analyses supporting drug development programs

Broader Multi-Modal Data Science (Clinical Trial & Drug Development)

• •Develop and apply computational methods for patient segmentation and biomarker discovery from multimodal clinical and omics datasets in partnership with Translational, Clinical, and Statistical Scientists
• •Execute data science and biomarker analyses on datasets from BMS clinical trials spanning genomics, proteomics, imaging, flow cytometry, and other high-dimensional biomarker data types
• •Perform innovative statistical analyses of high-dimensional data (e.g., gene expression, sequencing, imaging features) generated by cutting-edge technologies
• •Develop novel ways of integrating, mining, and visualizing, high-dimensional, and disparate data types, including integration of RWD with clinical trial data to