A Data Scientist, who must have a PhD qualification in a relevant field, with 1-2 years' of industry experience (desirable) is needed to join the team at this fast-growing Data Science company. This is a permanent position.They are a spin out company from the University of Cambridge Astrophysics group, applying cutting-edge data science and mathematics to solve a diverse range of problems.The company is looking for a candidate who has experience of Bayesian data science and has advanced coding skills in Python, and ideally has some experience of Fortran. The main focus of this role will be to advance their work in applying the core PolyChord technology to sample the free-energy surface of small molecules, in order to discover alternative small-molecules combinations that will reduce the environmental footprint of industrial processes including mining. They are also pursuing applications of this method to small-molecule drug discovery.The company offers flexible working, and operates a hybrid arrangement with 1-2 days per week spent at their central office in Herne Hill, South London. London-based data scientists are welcome to work full time from the office if desired.Key Responsibilities:Work effectively with clients, collaborators, and the rest of the technical team to deliver new and innovative data analysis pipelines across a range of projects.Understand and apply Bayesian analytical techniques for optimisation, predictive maintenance, small molecule structure investigation and any other future projects that require it.Effectively utilise machine learning to create emulators for complex industrial simulations, as well as for the classification of infrastructure issues, as projects require it.Work to develop integrations of company core technology.Attend regular group meetings (online), and external collaboration meetings and networking events (some in person).Daily update and interfacing with the technical team.Write technical reports and documentation for code and technical pipelines.Write and maintain test modules for all code.Required Experience and Qualifications:PhD (Physics, Astrophysics, Statistics, Mathematics, Computer Science, etc.)1-2 years of experience in applying data science and statisticsUnderstanding of and interest in predictive modelling, machine learning, knowledge of regression, clustering and classification techniques, knowledge of Bayesian inference and model selectionFluency in programming languages, e.g. Python (essential), C, C++, Fortran, Java, SQLFamiliarity with Big Data frameworks and knowledge of issues relating to dimensionality and variables in modellingExtensive experience using Git version controlBenefits:Hybrid working5% pension allowanceSounds interesting? Click the APPLY button to send your CV for immediate consideration. It is essential for you to include a link to your github repository, and/or other examples of your coding.Candidates with previous experience or job titles, including; Data Scientist, Senior Data Analyst, AI Engineer, Data Architect, Statistician, Quantitative Analyst, Predictive Modeler, and Research Scientist (Data Science) may also be considered for this role.IND123