At Roche you can show up as yourself, embraced for the unique qualities you bring. Our culture encourages personal expression, open dialogue, and genuine connections, where you are valued, accepted and respected for who you are, allowing you to thrive both personally and professionally. This is how we aim to prevent, stop and cure diseases and ensure everyone has access to healthcare today and for generations to come. Join Roche, where every voice matters.
The Position
We are seeking an intern who recently pursued a BSc or MSc program with experience in computational structural biology and/or machine learning. You will join the “birthplace” of therapeutic proteins in Roche’s discovery unit and work on the development of novel machine-learning-based approaches for antibody design.
The objective of this project is to predict how antibodies bind their targets. Thus, you will be analyzing public and in-house data to identify characteristics of protein and antibody interactions. Based on this preliminary analysis, you will develop tailored structure-based machine learning methods to predict antibody-antigen binding affinity. Tailored machine learning architectures such as geometric GNNs will be applied for this project.
This project plays a role in significantly accelerating the design of therapeutic antibodies. You will have the opportunity to disseminate your findings to our cross-functional project teams, contributing to Roche’s innovative research efforts.

PREFERRED EXPERIENCE AND COMPETENCIES:

• Knowledge of software development and fluency in Python.
• Understanding of machine learning frameworks (e.g., PyTorch, Jax, TensorFlow).
• Experience with antibody informatics, protein structural modeling, and protein-protein interaction characterization. Experience in data mining methods is a plus.
• Familiarity with technologies required to undertake analyses on large data sources or with computationally intensive steps (Linux, HPC cluster computing)
• Strong communication and collaboration skills.
• Experience implementing reproducible research practices like version control (e.g., using Git) is a plus.

QUALIFICATIONS REQUIRED:

• MSc degree candidate or recent graduate in Bioinformatics, Statistics, Biomedical Engineering, Computer Science, or a related field with a Biology background.

• Collaborate with the host team to evaluate potential antibody design techniques and applications.
• Develop and interpret machine learning algorithms to address selected research questions, including model selection and data preparation.
• Proactively share learnings and knowledge to support the development of the wider Roche computational community.
• Help shape the direction of machine learning and artificial intelligence within Roche.