Principal Data Scientist, AI/ML

With the advancement of large-scale data with different modalities and new technology, data science is becoming an integral part of R&D. It plays the important role of connecting data, insights generation with advanced methodology and the underlying scientific questions across many stages in R&D to enable data-driven decision making. This requires the development of relevant data strategy, the buildup of fit-for-purpose data platform and foundation, and applications of the most effective computational methods to address the key questions.

In this role, he/she is accountable for directing the application of scientific domain-specific knowledge (bioinformatics) and/or clinical disease area expertise, specialized data processing techniques, analytical and machine learning capabilities to extract scientific insight and enable hypotheses generation from data. He/she will drive the application of foundational and innovative techniques to coordinate the delivery of Bioinformatics solutions to facilitate translational and clinical decision-making activities.

Major responsibilities

• Coordinate the implementation of novel informatics solutions grounded in a specialized area (bio and clinical informatics) designed to drive the interrogation of datasets for insights in scientific and clinical application areas within defined project scope.  This includes integrating complex data from multiple sources and modalities (e.g., signal pathway analysis, cellular characterization, multi-omics, real world evidence, clinical trials).
• Using domain-specific understanding, translates unstructured, complex scientific and clinical problems into the appropriate data problem, and design and implement informatics solutions.
• Build and manage effective relationships with wide range of stakeholders (such as clinicians and biological researchers) to ensure utilization and value of information resources, such as combine phenotyping data with large clinical datasets including NGS-based DNA and bulk RNA results for integrative analysis.
• Develop and apply ongoing knowledge and awareness in trends, standard methodology and new developments in analytics and data science to shape solutions.
• Clearly and objectively communicate results, as well as their associated uncertainties and limitations.
• Stay actively involved in the healthcare and AI research community. Collaborate with academic and industry partners to advance ML/AI applications for drug development.
• Support and drive publications in high quality scientific, technical, or medical journals.
• Participate and thrive in an interactive, team-oriented culture.

Education, Qualifications, Skills and Experience

• Advanced degree in computer science, statistics, mathematics, engineering or related field. PhD is preferred.

• Track records with developing, implementing and deploying programs and computational solutions employing Machine Learning/Deep Learning (GNN, Geometric deep learning, Diffusion models, LLM etc.) to solve scientific questions from pharma R&D
• Proficiency in programming languages commonly used in AI research, such as Python, and TensorFlow/PyTorch.
• Solid knowledge of machine learning concepts, including deep learning, optimization algorithms, regularization techniques, and model
• Experience with solution architecture development and deployment
• Experience with building and maintaining software systems in collaboration with other using version control tools.

• A strong understanding and solid hands-on experience of RDBMS and SQL systems, analytics platform, Java and Python, ETL, Hadoop, Spark, Yarn, Kafka, and other tools is necessary. Knowledge of hardware required for effective database operations.
• Creative problem-solver with excellent communication skills - able to convey complex concepts to technical and business teams in a simple and understandable way.
• Agile experience is a plus.

Date Posted

Closing Date

AstraZeneca embraces diversity and equality of opportunity.  We are committed to building an inclusive and diverse team representing all backgrounds, with as wide a range of perspectives as possible, and harnessing industry-leading skills.  We believe that the more inclusive we are, the better our work will be.  We welcome and consider applications to join our team from all qualified candidates, regardless of their characteristics.  We comply with all applicable laws and regulations on non-discrimination in employment (and recruitment), as well as work authorization and employment eligibility verification requirements.