Senior Scientific Software Engineer, Analytics and Workflows

The Position

A healthier future. It’s what drives us to innovate. To continuously advance science and ensure everyone has access to the healthcare they need today and for generations to come. Creating a world where we all have more time with the people we love. That’s what makes us Roche.

Advances in AI, data, and computational sciences are transforming drug discovery and development. Roche’s Research and Early Development organisations at Genentech (gRED) and Pharma (pRED) have demonstrated how these technologies accelerate R&D, leveraging data and novel computational models to drive impact. Seamless data sharing and access to models across gRED and pRED are essential to maximising these opportunities. The new Computational Sciences Center of Excellence (CoE) is a strategic, unified group whose goal is to harness this transformative power of data and Artificial Intelligence (AI) to assist our scientists in both pRED and gRED to deliver more innovative and transformative medicines for patients worldwide.

The Analytics and Workflows group within the Center of Excellence (CoE) is dedicated to turning complex data into actionable insights that advance drug discovery and development. We leverage cutting‑edge high‑throughput technologies and foundational multimodal machine learning models to analyze large‑scale biological data, enabling deeper understanding of disease mechanisms and the identification of novel therapeutic opportunities. Despite advances in these fields, however, transforming raw data and computational models into meaningful biological insights remains a key challenge.

In this role, you’ll work at the intersection of data science, biology, and engineering to build innovative analytical tools that bridge the gap between data generation and biological interpretation—helping unlock new avenues for scientific discovery and impact. Genentech seeks a talented and highly motivated Bioinformatics Software Engineer with expert knowledge of reproducible and scalable analysis of bulk and single cell datasets for target and biomarker discovery.

• The primary focus of this position is to establish new and maintain existing workflows, libraries and stand‑alone tools for the analysis of transcriptomics and epigenetic data at the bulk and single cell level.
• You will evaluate, refine, and product ionize analytical workflows that enable our scientists to interrogate biology and make drug pipeline relevant decisions.
• You will deeply engage with computational scientists to understand their analytical needs and turn these into reusable components. To achieve this outcome you confidently evaluate and combine open-source, commercial and in‑house developed solutions.
• You will collaborate with interdisciplinary teams of Software Engineers, Computational Biology and Data Scientists to develop scientific workflows and tools that make this data available to machines and humans using a variety of interfaces.

• You have a PhD in Software Engineering, Computer Science, Bioinformatics, or similar and 2 years of relevant experience in a clinical, academic or commercial setting. Alternatively, a Masters degree or equivalent and at least 5 years of relevant experience.
• You have expert knowledge of R package development, and are familiar with the core R and Posit package development and deployment toolchain.
• You have successfully analyzed large datasets using R and are familiar with major tools and statistical methods used during the analysis of single cell and bulk data.
• You understand transcriptomic and epigenetic analysis well enough to identify, diagnose and mitigate unlikely or surprising results.
• You have successfully delivered a software project throughout the whole development cycle (planning, implementation, testing, release, maintenance) following modern software development practices and are using AI expert assistance at all stages of your work.
• You can effectively integrate, reshape and analyze multimodal biological data in state‑of‑the‑art scalable data formats (e.g., Parquet, tile
  
  DB, Zarr, H5)
• You are comfortable working with MCPs, REST APIs and other modern data science…