About the Company
Caspian technology solutions enable banks to automate the complex human tasks of risk investigation and decision making in Financial Crime and Compliance. Caspian are a development partner for Nasdaq following significant investment. In areas such as Anti-Money Laundering and Customer Due Diligence, global banks harness large numbers of human analysts in a continual effort to investigate and to mitigate risk. Caspian transform risk and efficiency for global banks, through machine intelligence solutions that can automatically read, analyse and make judgements as well as the very best human experts.
Job Role
As a junior data scientist in Caspian, you will be involved in:
- Developing and analysing machine learning and statistical models to automate risk judgements in AML investigations
- Supporting client projects with global banks, providing analytical insight and high quality data science input
- Developing machine learning product features, from research and prototype through to production-ready implementations
- Developing quality code in python, using software engineering best practices
- Working collaboratively in a cross-functional development team
- Communicating model results and analysis to key stakeholders
- Developing domain knowledge in anti-money laundering, as well as technical knowledge in machine learning
Required
- Programming experience, demonstrated through coursework or personal projects
- Knowledge of machine learning algorithms and/or statistical data analysis techniques
- Bachelor’s in a quantitative subject (e.g. Computer Science, Mathematics) or equivalent industry experience
- Strong problem-solving skills
- Self-motivated, flexible and proactive with excellent team-work skills
- Good verbal and written communication skills
- You must have the legal right to work in the UK to apply for this role as this company are unable to support Visa Applications/Sponsorship
Beneficial
- Experience with Python
- Experience in a machine learning framework: e.g. Tensorflow, Scikit-learn, keras, PyTorch
- Solid understanding of statistics and linear algebra
- Knowledge of one or more of the following key topic areas: Natural Language Processing, Deep Learning, Supervised and Unsupervised Learning, Bayesian Statistics
- Awareness of software engineering best practices e.g. version control, testing