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

About the role

Roche's Pharmaceutical Research and Early Development (pRED) organisation, specifically its DELT team in Molecular Discovery Technologies, is looking for a Scientific Data Scientist & Engineer for DNA-Encoded Library Technology. The role sits at the intersection of chemical biology, cheminformatics and data science, turning complex screening data into actionable insights and building automated workflows that accelerate hit identification in small-molecule drug discovery.

Key responsibilities

• Apply statistical methods, predictive models and advanced analytical approaches to large-scale DEL screening datasets, identifying promising chemical starting points and supporting hit and lead discovery.
• Develop intuitive analytical tools and workflows so screening scientists and project teams can quickly evaluate selection results and prioritise compounds.
• Design, implement and maintain automated, reproducible data processing and analysis pipelines.
• Build computational workflows and searchable building-block data resources for chemical space exploration, reaction prediction, library design and synthesis strategy.
• Partner with experimental scientists, computational chemists and machine learning teams to turn scientific challenges into scalable computational solutions.
• Present analytical results and technical developments to scientific and multidisciplinary audiences.
• Promote reproducibility, data integrity and robust engineering practices in a safe, compliant research environment.

Required profile

• PhD or M.S. in Bioinformatics, Statistics, Computer Science, Data Science, Cheminformatics, Software Engineering or a related quantitative field.
• Strong software engineering background with experience deploying pipelines at scale in HPC or cloud platforms.
• Proven experience in high-throughput scientific data analysis (large-scale screening data, DEL selection outputs or NGS pipelines) and building user-friendly tools for non-expert scientists.
• Understanding of hit triaging, noise reduction, statistical ranking and signal verification in large datasets.
• Cheminformatics and laboratory data systems (LIMS, SQL, relational databases) are a plus.

Required skills

• Python and statistical programming
• Data visualisation frameworks such as Spotfire, Tableau or modern web dashboarding tools
• Cheminformatics tools such as RDKit or OpenEye (a plus)