At GSK, the business and technical problem is to develop novel therapies for existing and emerging diseases by applying advanced machine learning and AI techniques to drug development, aiming for better outcomes at reduced cost and fewer side effects.
Requirements
- Experienced in developing deep learning models.
- Experience with standard deep learning algorithms and model architectures.
- Familiarity with current deep learning literature and math of machine learning.
- Knowledge in machine learning best practices, scalable training and deployment, model introspection and evaluation.
- Experience in PyTorch, Tensorflow, or other deep learning frameworks.
- Experienced/accomplished in software engineering with advanced skills in python and/or C++
- Experience with devops stacks: version control, CI/CD, containerization, etc
Responsibilities
- Develops SOTA deep learning models for solving challenging real world scientific problems.
- Converts vaguely described biological/drug discovery challenges into well-defined machine learning problems.
- Independently executes and delivers full AI/ML driven solutions from sourcing training data, design and implementing SOTA machine learning models, testing, benchmark and product driven research for model performance improvement, to shipping stable, tested, performant code and services in an agile environment.
- Models viral evolution using large scale datasets and emerging AIML techniques.
- Applies machine learning and AI methods to questions at the start and end of the journey of drug development.
- Designs and implements SOTA machine learning models.
- Ships stable, tested, performant code and services in an agile environment.
Other
- Graduate studies in Computer Science or Applied Math, undergraduate studies in Computer Science and relevant graduate studies in the life sciences with a focus on AI/ML techniques, or undergraduate studies in Computer Science and equivalent work history.
- Scientist, machine learning engineer, and software engineer with expertise and depth in at least one area.
- PhD in Machine Learning.
- Knowledge in disease biology, molecular biology and virology.
- Experience with biological data (e.g., genomics, transcriptomics, epigenomics, proteomics).
