Risk & Data Analyst
As a Data & Risk Analyst you will be a crucial member of a team responsible for developing a bespoke lending platform that has recently been accredited as being far more advanced than any other product on the market. We have ambitious plans to transform the face of SME lending and we have already made waves in the industry.
Our Data & Risk Analyst develop cutting edge algorithms using statistical modelling and machine learning techniques. Using Python (Pandas, NumPy and SciPy) they work in a fast paced and dynamic environment to produce data driven solutions. Our Tech & Analytics team works in a relaxed, collaborative and flexible environment, where everyone has the opportunity to make a significant contribution to the business. You will be expected to derive meaningful and actionable insights from our data as well as develop the innovative technologies behind our platform.
We are looking for Analyst who love to code and get their hands dirty with raw data. It doesn't really matter whether people call you an Engineer, Physicist or Mathematician, what matters to us is that you are a curious and continuous learner with a hunger to achieve the very best in what you do.
- We are a team of 7 with a real love for mathematical and statistical modelling
- We all play a significant role in specifying the problem and thinking through all possible solutions
- Our development cycle is tight with Agile-ish processes that means features or projects go live in days or weeks rather than months or years
- Strong Numerate background, e.g Degree in Engineering, Mathematics, Physics or equivalent
- Must have a background in Probability & Statistics
- Programming experience: Python, Java, C/C++ or similar
- Self-starter with ability to work autonomously in an unstructured environment
- Demonstrable experience using machine learning techniques
- Strong basis in computer-science fundamentals
- Experience with Pandas, NumPy, SciPy, R, Matlab, and/or SQL.
- Understanding of web technologies
Experience in scorecard building and credit / fraud models