Principal Scientist – Cheminformatics – GSK, Stevenage, UK

Job Description

This role sits within the Data, Automation and Predictive Sciences (DAPS) division of GSK’s Research & Development (R&D) function and reports into the Senior Director for Cheminformatics.  The Data, Automation, and Predictive Sciences (DAPS) function of GSK Research Technologies focuses on large-scale data generation, curation, analysis, and prediction to increase the Probability of Technical and Regulatory Success (PTRS) of assets.
Job purpose:
The Principal Scientist role (within the Cheminformatics group) uses large proprietary internal datasets to develop, integrate and embed advanced computational methods and predictive in-silico models to accelerate the discovery of medicines.  With a focus on machine learning, cheminformatics and computational chemistry methodologies, you will help drive the development and delivery of key new capabilities for our internal automated small molecule design platform coupled directly to lab automation.
At GSK we currently have a major R&D initiative focused on transforming small-molecule drug discovery.
Please Note - Location: This role will temporarily be based at Stevenage.  However, the Company plans to relocate its offices to Cambridge, UK. The location of this role will therefore subsequently change to Cambridge UK, in accordance with timelines to be set by the Company.  The relocation is currently proposed to take effect by early 2029.
About You:
This role is a great opportunity to be instrumental in developing and delivering subject matter expertise across GSK.  As this role is multi-faceted and includes collaborating / liaising with a wide variety of stakeholders and matrix teams you must have strong experience of working in complex technical situations, with demonstrable clear problem-solving approach to your work.  Strong people skills and a proven ability to influence people to achieve and drive performance are also pre-requisites for this role.

Key Responsibilities

• Build, validate and deploy cheminformatics and machine learning methods and models to inform go/no-go across drug-discovery programmes.
• Integrate with drug discovery programme teams (including DMPK, Toxicology and Safety Pharmacology) to embed predictive models directly into decision-making and translate computational outputs into guidance that is accessible to non-experts.
• Prototype exploratory, agent-driven workflows that combine LLM-based reasoning with cheminformatics tools, predictive models and experimental data to accelerate hypothesis generation, literature and data triage, and iterative design / make / test / analyse cycles.
• Contribute to and validate production-quality code implementing state-of-the-art cheminformatics, computational chemistry and quantum chemistry methods that accelerate and improve decision-making on drug discovery programmes.
• Prepare and present results of key validation experiments, details of capability builds, and developments on drug discovery projects to internal and external groups in a way that is both informative and accessible to the non-subject matter expert.
• Work with others within a multidisciplinary matrix team that spans different organizations and geographies to execute on joint aims.

Qualifications

• Relevant degree-level education (eg; PhD or MSc in Cheminformatics, Computational Chemistry, Informatics, Life Sciences) or equivalent with a strong Chemistry foundation.
• Knowledge / Experience of programmatically collecting, combining, mining and analysing complex biological and chemical data to build predictive models.
• Broad knowledge of computational sciences including machine learning, computational chemistry and cheminformatics methods.
• Knowledge / Experience of computer programming and scripting languages (eg; Python, Java, C/C++, R).

Skills Required

• Knowledge of related disciplines (medicinal chemistry, HT screening, analytical chemistry, systems biology, DMPK, Tox) to enable multidisciplinary approaches to be identified and integrated into a cohesive project plan is preferred.
• Expertise with chemical toolkits such as ChemAxon, RDkit and scientific pipelining tools such as Pipeline Pilot, KNIME
• Skills: Artificial Intelligence (AI), Computational Sciences, Computer Programming, Data Analysis, Data Management, Data Modeling, Data Science, Predictive Modeling, Statistical Models

Additional Information

Always verify vacancy details and availability on the employer’s official website. Jobs Bio Help Learning is an independent job-discovery platform and does not process applications.