Our mission at Xyme is to solve important societal problems by revolutionising the practice of synthetic chemistry through what we call xymes - AI-generated enzymes that can catalyse any reaction. As an innovative startup based in Oxford and Manchester, UK, we bring together interdisciplinary teams of scientists, engineers, and data specialists to push the boundaries of enzyme design. Our dynamic and collaborative work environment is fuelled by a passion for innovation. We cultivate a culture of continuous learning and improvement, where every team member can make a lasting impact on our groundbreaking research and real-world applications.
As a (Senior) Research Scientist in Multi-fidelity Learning at Xyme, you will play a crucial role in developing and deploying methods that leverage both experimental and digital data to drive continual learning cycles. Your expertise in state-of-the-art learning paradigms and multi-modal models will be instrumental in advancing our AI-driven enzyme design platform. You will work in a highly interdisciplinary team interfacing with simulation, enzyme design, and experimental labs to establish a design make test learn cycle that operates under real-world constraints and uncertainties, ultimately contributing to our mission of revolutionising synthetic chemistry.
What you will do
* Develop and implement cutting-edge multi-fidelity learning methods that combine experimental and computational data to enhance our enzyme design capabilities.
* Design and deploy active learning, Bayesian optimisation, and evolutionary design strategies to optimise our AI-generated enzyme design process.
* Create and refine multi-modal models, such as multi-head neural networks and multi-output Gaussian processes, to integrate diverse data sources effectively.
* Develop learning models that can operate under various constraints (cost, accessibility, etc.) and handle uncertainty and noise in data.
* Scale and deploy learning algorithms within our complex ecosystem, ensuring they perform efficiently beyond toy problems.
* Collaborate closely with research scientists, data engineers, and other team members to integrate your work into our broader AI enzyme design platform.
* Contribute to the continuous improvement of our data-driven approaches and help establish best practices for multi-fidelity learning in our organisation.
What you will bring
* A PhD in Machine Learning, Computer Science, Applied Mathematics, or a related field with a focus on multi-fidelity learning or similar approaches.
* Extensive experience with state-of-the-art learning paradigms, including active learning, Bayesian optimisation, and evolutionary design.
* Strong expertise in developing and implementing multi-modal or multi-fidelity models, such as multi-head neural networks and multi-output Gaussian processes.
* Proven track record of creating learning models that operate under real-world constraints and can handle uncertainty and noise in data.
* Experience in deploying learning algorithms at scale within complex ecosystems, demonstrating their effectiveness in an industry setting.
* Proficiency in Python and relevant machine learning libraries (e.g., PyTorch, TensorFlow, scikit-learn).
* Excellent problem-solving skills and the ability to translate complex mathematical concepts into practical solutions.
* Strong communication skills and the ability to collaborate effectively in an interdisciplinary team.
Nice to have
* Experience in computational chemistry, bioinformatics, or related fields relevant to enzyme design.
* Familiarity with high-performance computing environments and distributed computing frameworks.
* Knowledge of software engineering best practices, including version control, testing, and continuous integration.
* Publications or contributions to open-source projects in the field of multi-fidelity learning or related areas.
What you will get from us
* The opportunity to work on groundbreaking technology with real-world impact, making significant contributions to synthetic chemistry and enzyme design.
* A supportive and collaborative work environment that nurtures creativity and innovation, providing genuine ownership and autonomy.
* Continuous learning and development opportunities, including the chance to attend and present at relevant conferences and industry events.
* The excitement of being part of a fast-growing startup at the forefront of AI-driven enzyme design.
* Competitive compensation and benefits package commensurate with your skills and experience.
#J-18808-Ljbffr