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 the 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.
Requirements
- strong background in scientific software development and ML engineering, with demonstrated ability to design, train, and deploy ML models.
- experience working with biochemical, chemical, or biophysical datasets; familiarity with cheminformatics and small molecule drug discovery concepts.
- fluent in Python and experience with modern ML frameworks (e.g., PyTorch, JAX, TensorFlow, Hugging Face)
- familiarity with commonly used toolkits for chemical modeling (e.g., RDKit, OpenEye, OpenMM, Schrodinger)
- Experience with cloud platforms (AWS, GCP, or Azure), version control (Git), and CI/CD pipelines.
- Record of scientific excellence as evidenced by at least multiple publications in a scientific journal or conference.
- Public portfolio of projects available on GitHub/GitLab is a plus.
Responsibilities
- Design, build, and apply machine learning methods to key challenges in small molecule drug discovery, including molecular property prediction, protein–ligand modeling, chemical reactivity, and synthesizability.
- Develop robust and scalable ML pipelines that integrate with cheminformatics, structural biology, and computational chemistry tools.
- Collaborate with computational chemists, medicinal chemists, structural biologists, and experimental scientists to generate testable hypotheses and guide design decisions.
- Curate, integrate, and leverage diverse biochemical, biophysical, and chemical datasets to power ML models and workflows.
- Explore and apply a range of ML approaches — from deep learning (transformers, graph neural networks) to physics-informed and hybrid methods — for impactful applications in drug discovery.
- Deploy models and workflows into production research environments, ensuring reproducibility and scalability.
- Contribute to and drive publications, present results at internal and external scientific conferences, and help make code and workflows open source.
Other
- PhD in the physical sciences (e.g., Chemistry, Physics, Chemical Engineering) or quantitative fields (e.g., Computer Science, Statistics, Applied Mathematics) with 0 - 3 years experience, or equivalent industry research experience.
- Relocation benefits are available for this job posting.
