Data Scientist / Engineer - DNA-Encoded Library Technology (DELT)

Description

The DELT team sits in Molecular Discovery Technologies within the Small Molecule Research Discovery department, part of Therapeutic Modalities in pRED. The team supplies high-quality chemistry starting points for small-molecule projects and produces molecular and mechanistic insight that moves discovery projects forward. Its work spans high-throughput and focused screening, DNA-encoded library technology, protein science and biophysics, cell-based assays, biostructure determination, computer-assisted drug design, and medicinal chemistry.

The role sits at the meeting point of chemical biology, cheminformatics and data science. You would help build the next generation of data-driven DELT by combining statistical analysis, scalable data engineering and advanced computational methods. The work turns complex screening results into scientific decisions and supports hit identification for small-molecule discovery.

You would work alongside experimental scientists, computational chemists and machine learning specialists to connect new science with practical implementation, making decisions across the DELT platform more informed, reproducible and efficient.

Responsibilities

• Apply statistical methods, predictive models and analytical techniques to large DEL screening datasets, identifying promising chemical starting points and supporting hit and lead programs.
• Build clear, easy-to-use analysis tools and workflows so DELT screening scientists and project teams can review selection results, rank compounds and decide next experiments.
• Design, build and maintain automated, reproducible pipelines that turn raw experimental output into reliable results ready for decisions.
• Develop computational workflows and searchable building-block data to support chemical space exploration, reaction prediction, library design and synthesis planning.
• Work with experimental, computational chemistry and machine learning teams across the small-molecule research organisation to turn changing scientific problems into scalable software solutions.
• Present analytical results, methods and new technical capabilities clearly to scientific and cross-disciplinary audiences.
• Promote reproducibility, data integrity and sound engineering practice, and help keep the research environment safe and compliant.

Requirements

• Strong drive toward DNA-encoded library technology, a wish to push its limits, and appetite for new challenges.
• A motivated data scientist keen on chemical biology and on advancing the technology, with interest in state-of-the-art research in the pharmaceutical industry.
• A PhD or M.S. in bioinformatics, statistics, computer science, data science, cheminformatics, software engineering or another related quantitative field.
• A solid software engineering background, including deploying pipelines at scale on HPC or cloud platforms.
• Proven experience analysing high-throughput scientific data, ideally large screening datasets, DEL selection outputs or NGS pipelines, and building reliable, user-friendly tools that let non-expert scientists run complex analyses.
• Strong Python and statistical programming skills, plus experience with visualisation tools such as Spotfire, Tableau or modern web dashboard frameworks.
• Understanding of hit triage, noise reduction, statistical ranking and signal verification in large datasets. Cheminformatics skills, such as handling chemical structures, building-block metadata or toolkits like RDKit or OpenEye, and experience with LIMS, SQL or relational databases are a plus, as is connecting computational tools to lab workflows.
• A critical, solution-minded thinker with a habit of continuous improvement and a record of designing scalable scientific solutions, plus the communication skills to explain quantitative findings to non-quantitative colleagues.

Conditions

The company is an equal opportunity employer.