Data Scientist - Real World Data - Data42

Job Description Summary

Are you passionate about the intersection of data, technology and science, and excited by the potential of Real-World Data (RWD) and AI? Do you thrive in collaborative environments and aspire to contribute to the discovery of groundbreaking medical insights? If so, join the data42 team at Novartis!
At Novartis, we reimagine medicine by leveraging state-of-the-art analytics and our extensive internal and external data resources. Our data42 platform grants access to high-quality, multi-modal preclinical and clinical data, along with RWD, creating the optimal environment for developing advanced AI/ML models and generating health insights. Our global team of data scientists and engineers utilizes this platform to uncover novel insights and guide drug development decisions.
As an RWD SME / RWE Execution Data Scientist, you will focus on executing innovative methodologies and AI models to mine RWD on the data42 platform. You will be the go-to authority for leveraging diverse RWD modalities patterns crucial to understanding patient populations, biomarkers, and drug targets, accelerating the development of life-changing medicines.

 

Job Description

Duties and Responsibilities:

• Collaborate with R&D stakeholders to co-create and implement innovative, repeatable, scaleable and automatable data and technology solutions in line with data42 strategy.
• Be a data SME, understand RWD of different modalities, vocabularies (LOINC, ICD, HCPCS etc.), non-traditional RWD (Patient reported outcomes, Wearables and Mobile Health Data) and where and how they can be used, including in conjunction with clinical data, omics data, pre-clinical data, and commercial data.
• Contribute to data strategy implementation such as Federated Learning, tokenization, data quality frameworks, regulatory requirements (submission data to HL7 FHIR formats conversion, Sentinel initiative), conversion to common data models and standards (OMOP, FHIR, SEND etc.), FAIR principles and integration with enterprise catalog
• Define and execute advanced integrated and scaleable analytical approaches and research methodologies (including industry trends) in support of exploratory and regulatory using AI models for RWD analysis across the Research Development Commercial continuum by facilitating research questions.
• Stay current with emerging applications and trends, driving the development of advanced analytic capabilities for data42 across the Real-world evidence generation lifecycle, from ideation to study design and execution.
• Demonstrate high agility working across various cross-located and cross-functional associates across business domains (commercial, Development, Biomedical Research) or Therapeutic area divisions for our priority disease areas to execute complex and critical business problems with quantified business impact/ROI.
• Draft and edit high-level research documents (proposals, protocols, statistical analysis plans). [optional]
• Knowledge of governance, ethical and privacy considerations [optional]

Ideal Candidate Profile:

• PhD or MSc. in a quantitative discipline (e.g., but not restricted to Computer Science, Physics, Statistics, Epidemiology) with proven expertise in AI/ML.
• 8+ years of relevant experience in Data Science (or 4+ years post-qualification in case of PhD).
• Extensive experience in Statistical and Machine Learning techniques: Regression, Classification, Clustering, Design of Experiments, Monte Carlo Simulations, Statistical Inference, Feature Engineering, Time Series Forecasting, Text Mining, and Natural Language Processing, LLMs, and multi-modal Generative AI.
• Good to have skills: Stochastic models, Bayesian Models, Markov Chains, Optimization techniques including, Dynamic Programming Deep Learning techniques on structured and unstructured data, Recommender Systems.
• Proficiency in tools and packages: Python, R(optional), SQL; exposure to dashboard or web-app building using PowerBI, R-Shiny, Flask, open source or proprietary software and packages is an advantage.
• Knowledge in data standards e.g. OHDSI OMOP, and other data standards, FHIR HL7 for regulatory, and best practices.
• Good to have: Foundry, big data programming, working knowledge of executing data science on AWS, DataBricks, SnowFlake
• Strong in Matrix collaboration environments with good communication and collaboration skills with country/ regional/ global stakeholders in an individual contributor capacity.
• High learning agility and adherence to updates in industry and area of work.
• Optional Experience in Biomedical Research and development in pharma is a bonus.

 

Skills Desired

Applied Machine Learning, Applied Machine Learning, Artificial Intelligence (AI), AWS Data Pipeline, Bayesian Models, Classification Systems, Clinical Trials, Common Data Model (CDM), Computer Data Storage, Computer Programming, Cross-Functional Teams, Data Analysis, Databricks Platform, Data Integration, Data Management, Data Science, Data Structures, Data Tokenization, Deep Learning, Fast Healthcare Interoperability Resources (FHIR), Feature Engineering, Federated Learning, HL7 Standards, Initiative, Markov Chains {+ 16 more}