On a mission to save 100k lives and $1.5B healthcare costs
medical devices • diagnostics • lung cancer • precision medicine • colon cancer
August 25
🔄 Hybrid – Cambridge
On a mission to save 100k lives and $1.5B healthcare costs
medical devices • diagnostics • lung cancer • precision medicine • colon cancer
• Be an innovative and creative part of a team of scientists and engineers developing novel approaches helping people and saving lives. • Contribute towards a wide spectrum of data science initiatives, including data acquisition and collection, testing and validation for experimental design. • Create and maintain effective data processing pipelines and data visualisation tools. • Develop new and refine existing methods and algorithms, in close collaboration with other scientists, to maximise experimental sensitivity and selectivity. • Develop and improve production-ready statistical and machine learning (ML) models. • Prepare reports, presentations, etc. to communicate key insights and findings to stakeholders. • Pro-actively seek learning and development opportunities and always aim to share knowledge with others. • Thrive in a dynamic environment that requires engagement with cross-functional projects and contribute towards the overall success of the team/group/department by advancing data-driven decision making.
• Degree in a quantitative/scientific subject. • Experience with Python and the PyData stack (e.g. NumPy, SciPy, pandas, matplotlib, scikit-learn, Keras, PyTorch). • Well versed in the fundamentals of data science (e.g. data science life cycle, data collection/processing, feature engineering, model selection) best practices. • Basic knowledge of software engineering (e.g. SOLID, software development life cycle, design patterns, architectures) best practices. • Expertise in probability, statistics and linear algebra. • Understanding of different machine learning algorithms and their domain applicability in a production environment. • Excellent interpersonal, oral and written communication skills. • Curiosity, eagerness to learn and a highly collaborative style. • Basic knowledge of biology and/or chemistry. • Experience in healthcare, biology or biotechnology. Experience working with mass spectroscopy-based metabolomics (or other omics data) derived from clinical trial or epidemiology/cohort studies is a plus. • Knowledge of targeted and non-targeted biomarker discovery. • Familiarity with database management systems (relational and document-based) and related Python frameworks. • Familiarity with Git, CI/CD best practices. • Familiarity with network analysis methods. • Familiarity with Agile methodologies and experience managing projects using Agile to ensure flexible and efficient project delivery. • Experience in recognising, quantifying and addressing sources of bias and variance.
Apply Now