Data Scientist, Biomarker and Clinical Data Analysis

Job description

Job Description

The Biomarker Development (BMD) department at Novartis Institutes for BioMedical Research (NIBR) is looking for a PhD/MD-qualified data scientist with experience in the development of novel methods and software for the ingestion, analysis and visualization of biologic and non-biologic multi-source data to join the multidisciplinary Quantitative Sciences and Innovation (QSI) group located in Basel, Switzerland.

Reporting to the Global Head of Integrative Data Sciences (IDS), you will be responsible for the identification and development of innovative analytical methods to cover project specific biomarker needs including but not limited to high-throughput genomics, multi-modal biological profiling and multivariate clinical data, mobile medical devices and real-world data (e.g. medical claims). You will be accountable for the execution of large volume data extraction, integration and analysis activities possibility including the implementation of a variety of Next Generation Sequencing and real-time mobile device data processing pipelines and the timely delivery of key project related milestones.

The Data Scientist will play a leading role in identifying and establishing new projects and collaborations, both internal and external, in designing and implementing new solutions and analytics and in ensuring the adoption and use of QSI Informatics applications across the different line functions and across NIBR.

Furthermore, you will have the chance to contribute to the planning and implementation of a QSI strategy for the organization, storage, visualization and analysis of very large datasets from Disease Areas (DA), NIBR, Development and external sources and their integration with internal data sources including clinical trials.

Specifically, main accountabilities include:

• Contribute to the planning and implementation of a global strategy for the ingestion and integration of data (biologic and non-biologic) from internal and external sources
• Contribute to the implementation of the Translational Medicine (TM) real-time/digital device vision in close collaboration with IT
• Interface with key leaders and scientists across NIBR and Novartis especially other bioinformatics groups, statistical and modelling teams to address and resource bioinformatic, computational and software development needs
• Maintain expertise in best practises for data handling especially as it applies to “big data” (data warehousing, data integration, ELN, archiving, hadoop, spark etc.)
• Provide internal (Novartis) and external scientific leadership on all data science methods and activities
• Identify, build and manage new collaborations with internal (Novartis) and external academic and industry groups
• Drive the development of new analytic methods in collaboration with internal NIBR/Development groups or external groups that address BMD/TM needs
• Independently seek out new sources of data that could be leveraged for TM/BMD/QSI needs
• Maintain a strong and positive relationship with IT and help to leverage their resources and expertise for TM/BMD/QSI needs

Desired profile

• PhD and/or MD required in biostatistics, bioinformatics, computer science, data science or discipline requiring intense data analysis
• Several years of post-graduate work experience in bioinformatics, medical informatics, clinical informatics or other forms of informatics within a biomedical research environment
• Documented experience in leading the development of data storage systems specifically for large possibility streaming data.
• Deep experience in one or more of the following: Exploratory Data Analysis techniques, Machine Learning, Model validation techniques and graph analytics techniques
• Deep expertise in one or more of the following: Bash, HTML5, PERL, Python and R
• Proficiency with several of the following: distributed and high performance computing, data visualization, data engineering, pipelining and wrangling tools
• Good knowledge of data management approaches e.g. relational databases, object stores, column stores, triple stores, graph stores, document stores desired
• An understanding of pan-omic technologies and hands on experience analyzing.
• Proven track record of leading the development and deployment of informatic systems and applications that are an integral part of drug discovery and technology development
• Experience with the analysis of next-generation sequencing data a plus
• Ability to establish effective collaborative relationships with cross-functional scientific teams
• Demonstrated ability to successfully build sustainable partnerships and alliances with external parties
• Ability to respond to changing needs and priorities quickly and efficiently
• Demonstrated organizational and problem-solving skills, aligning available resources to meet goals
• Strong communications skills and ability to represent the group within NIBR and throughout the wider scientific community
• Excellent interpersonal, cross-cultural and influencing skills
• Proven ability to work independently and collaboratively in multidisciplinary teams
• Fluent English (oral and written)