Over the coming decade, deep learning looks set to have a transformational impact on the natural sciences. The consequences are potentially far-reaching and could dramatically improve our ability to model and predict natural phenomena over widely varying scales of space and time. Our AI4Science team encompasses world experts in machine learning, computational chemistry, material science, quantum physics, molecular biology, fluid dynamics, software engineering, and other disciplines, who are working together to tackle some of the most pressing challenges in this field.   

For our lab in Cambridge, we are seeking Research Software Development Engineer (RSDE) candidates in the area of deep learning for material generation. The successful applicant is expected to contribute to cutting-edge technological developments of generative models, reinforcement learning, and graph neural networks for materials generation, which has the potential to discover breakthrough materials for a broad range of applications.

This is an exceptional opportunity to drive ambitious research in a highly collaborative, diverse and global team of other researchers and engineers, and to push the state of the art in machine learning for molecular modelling.   

Responsibilities

• Contribute to cutting-edge technological developments of deep learning models for material generation with strong engineering support 
• Work closely with an interdisciplinary team of researchers and engineers to translate algorithms into efficient implementations and roll out prototype systems to maximize research velocity.  
• Design and develop large-scale deep learning research pipeline for materials discovery. This includes infrastructure development, model scaling, dataset handling, data visualization, and resource management.  
• Coordinate with researchers across the larger organization to identify and address future engineering needs of the team.   

Qualifications

• Experience in research-oriented software engineering for deep learning. Demonstrated by a completed MSc or PhD, or similar technical achievements. Preferably experience in an industrial team. 
• Demonstrable ability to work in large-scale software engineering, following good engineering practices (e.g., familiarity with scrum and other agile processes, continuous integration, unit tests, documentation, type annotation, etc.)  
• Experience in building large scale deep learning research pipelines. Preferably experience working as a core developer of existing pipelines for molecular design (e.g., GuacaMol, Open Catalyst Project)
• Strong understanding of deep learning approaches. Preferably experience with deep learning for molecules, geometric deep learning, generative models, and reinforcement learning. 
• Demonstrable ability to work in an interdisciplinary collaborative environment, evidenced by effective communication of technical concepts to non-experts from different technical backgrounds. 
• Passion to see research have real-world impact on key challenges for society.