Director Oncology Data Science LMW

Novartis•Cambridge, MA

1d•Onsite

About The Position

About the role: #LI:Onsite The Oncology Data Science team in Biomedical Research supports the Oncology Disease Area with computational biology, Artificial Intelligence / Machine Learning (AI/ML), and data engineering for novel therapeutics across multiple drug modalities. As integrated scientists and engineers, we apply advanced analytics to pre-clinical and clinical projects, enabling progress in target discovery, drug development, and translational and clinical science. We seek a Director of Data Science to lead our global team of US and Europe-based data scientists specializing in Low Molecular Weight (LMW) drug development who will guide the LMW data science team, collaborate closely with Oncology stakeholders and Biomedical Research, and introduce innovative data-driven solutions to enhance our LMW portfolio and benefit patients.

Requirements

This position will be located at the Cambridge, MA site and will not have the ability to be located remotely.
This position will require 10% travel as defined by the business (domestic and/ or international).
Ph.D. in data science, computational biology or related fields, strong scientific mindset, with a deep understanding of biology, oncology and low molecular weight drug development process.
10+ years of experience in a data science role in oncology drug development.
Excellent leadership and management skills, with 5+ years of people management experience in the data science space.
Experience with Quality Control (QC) and data analysis for common assays, such as bulk RNA-seq, scRNA-seq and/or chromatin-based assays (ChIP-seq, ATAC-seq, Hi-C).
Strong expertise in quantitative and computational biology approaches, general AI/machine learning and statistical modeling techniques and a proven track record of delivering data-driven insights and solutions.
Excellent communication skills, with the ability to communicate complex data insights and recommendations to cross-functional teams and stakeholders.
Proven history of contributions to the scientific community in the form of papers and/or conference presentations.

Nice To Haves

Experience with AI/ML approaches specific to the low molecular weight field including computational chemistry and application of generative AI in chemistry.
Experience with cell line profiling, shRNA or CRISPR perturbation screens, high content cell imaging, proteomics or in vivo efficacy analysis.

Responsibilities

Lead and develop a global team of US and Europe-based data scientists, driving high-quality data science that is grounded in deep understanding of biology and applicable data science methodologies and approaches.
Co-develop and execute a data science strategy to enable and enhance innovation in the LMW drug development space.
Closely align with the Oncology Drug Development teams to represent the low molecular weight data science function and ensure effective embedding of data science in drug development teams and alignment on scientific direction.
Regularly interface with Oncology Disease Area leaders to align priorities and to effectively deploy resources.
Collaborate closely with the Oncology Data Science AI team and other teams such as generative chemistry teams on the development and implementation of innovative machine learning algorithms, AI models, and platforms to enable the delivery of predictive and prescriptive insights.
Actively engage with stakeholders within partner functions, such as IT, Chemistry and Technology departments and build strong partnerships and shared projects.
As a member of the Oncology Data Science Leadership team, contribute to Oncology Data Science overall direction and management, represent the low molecular weight portfolio as a function.
Closely collaborate with Oncology Data Science engineering teams to ensure team adherence to data standards, data governance and data strategy and ensure the application of best practices in analytics and high standards of reproducibility in research across the team.
Play a leading role in matrix teams such as Translational Data Science Clusters around disease areas or teams centered around key technologies such as genomics, proteomics, spatial technologies etc.
Present and externalize work of the team in conferences, abstracts and scientific journals.