Structural & Computational Biologist

We are looking for talented Senior Scientists to join Prescient Design, a division devoted to developing structural and machine learning based new methods for protein design within Genentech's Research and Early Development (gRED) organization. The successful candidate will lead the development and execution of novel integrations of structural-biology and machine learning methods for the analysis and design of proteins with special application to protein therapeutics. The Role: * You will join Prescient Design within gRED. Your peers will be machine learning scientists and computational biologists working on different areas of the life sciences. * You will closely collaborate with biologists and bioinformaticians across departments in the organization. * You will develop structural/computational biology workflows and/or machine learning methods to analyze existing, and design new, biomolecular structures * You will be expected to form close working relationships with protein therapeutic development efforts across the gRED organization. * You will be expected to contribute to and drive publications, and present results at internal and external scientific conferences. Qualifications: * PhD degree in a quantitative field (e.g. Computer Science, Computational Biology, Physics). * Demonstrated experience with Python and analysis of protein structure and/or sequence data. * Record of achievement, including at least one high-impact first author publication or equivalent. * Excellent communication and collaboration skills. Additional desired qualifications: * Familiarity with at least one deep learning framework for neural networks (e.g., PyTorch; TensorFlow-Keras). * Experience with structural modeling platforms such as those devised to model and design biological macromolecules (e.g., Rosetta; OpenMM; Modeller). * Focus on one of these areas: antibody optimization or discovery, protein structure, computational chemistry. * Public portfolio of computational projects (available on e.g. GitHub).

#06022021