Senior Manager, Data Scientist

Role Summary

Senior Manager, Data Scientist (Biomarker) leading a new Drug Development Data Science and Biomarker team. You will translate complex multimodal data (clinical, omics, real-world) into testable hypotheses using classical ML and deep learning. You will develop and apply computational methods for biomarker discovery, lead predictive models, and drive biomarker strategy across clinical drug development. This role requires strong computational, statistical, and biological capabilities and the ability to collaborate with cross-functional teams.

Responsibilities

• Develop and apply novel or existing computational methods for patient segmentation from multimodal clinical and omics datasets for various treatment modalities in partnership with Translational, Clinical and Statistical Scientists
• Partner with lead and protocol statisticians in writing, reviewing and executing protocols and statistical analysis plans (SAP) for biomarkers and diagnostics, highlighting the biomarker strategy for clinical drug development
• Execute biomarker analyses on datasets from BMS clinical trials and real-world data cohorts
• Perform relevant and innovative statistical analyses of high-dimensional (e.g. gene expression, sequencing) data generated by cutting edge technologies
• Execute and contribute to the scientific and statistical strategy of drug development, including development of predictive biomarker(s) and precision medicine
• Optimize and validate biomarker assays for clinical trial usage.
• Develop, implement, and apply state-of-the-art algorithms to address key business problems and drive the implementation of innovative statistical methods in support of biomarker strategy
• Formulate, implement, test, and validate predictive models and implement efficient automated processes for producing modeling results at scale.
• Responsible for collaborating with cross-functional teams, including but not limited to clinicians, data scientists, translational medicine scientists, statisticians, and IT professionals.
• Manage and coordinate resources to produce quality deliverables within timelines for competing priorities.

Qualifications

• Required: Ph.D. in a relevant quantitative field (i.e. Computational Biology, Biostatistics, Statistics, Computer Science, etc.) and 1+ years of academic/industry experience or Master's Degree in a relevant quantitative field and 3+ years of industry experience
• Required: Strong experience in the analysis of data generated by one or more -omics or molecular assays
• Preferred: Knowledge of molecular biology, understanding of disease pathways
• Required: Strong experience in biomarker data analysis with data generated from clinical trials, or electronic health records
• Required: Experience in modeling methods particularly in their application to pharma R&D; Experience in the application of AI/ML, and proficient in SQL, Python, and R and cloud platforms
• Required: Experience developing statistical and machine learning models on high dimensional and high throughput data for time to event data and longitudinal outcomes
• Preferred: Perspective in leveraging innovative approaches to expedite drug development and address the complexities of emerging data
• Required: Ability to work both independently and collaboratively, and to handle several concurrent, fast-paced projects
• Required: Strong problem-solving and collaboration skills, and rigorous and creative thinking
• Required: Excellent communication, data presentation, and visualization skills
• Required: Capable of establishing strong working relationships across the organization

Skills

• Programming: SQL, Python, and R; cloud platforms
• Experience applying AI/ML to pharma R&D
• Strong data analysis and visualization capabilities