Lead Data Scientist - Receive Risk

Description

The company is a global technology business that moves and manages money internationally. This Lead Data Scientist role sits in London on the Receive team.

The work sits behind the scenes of transactions. You help balance risk controls with a smooth experience for customers who receive and add funds, and what you build affects the company's mission and millions of customers.

You will use data science to find, design and launch models that improve how customers receive and add money. The aim is sounder decisions, better customer outcomes and scalable data science for a growing product area. You will work alongside engineering, product, analytics, operations and risk.

Responsibilities

• Lead the building and launch of machine learning models and data science solutions that improve the Receive product across the company's markets.
• Dig into large amounts of customer, transaction and product data to spot trends, patterns, risks and opportunities.
• Design and run experiments that test product changes, decisioning systems and customer experience work.
• Create scalable modelling methods that support prioritisation, personalisation, risk management and day-to-day operational decisions.
• Work with analysts, product managers, engineers, operations and risk staff to turn business needs into practical data science solutions.
• Build robust data pipelines, algorithms and tools for production modelling and decision-making.
• Keep up with new developments in data science, machine learning and payment fraud prevention so the Spend domain stays at the cutting edge.

Requirements

• A proven record of deploying models end to end, covering data preprocessing, feature engineering, model selection, evaluation and monitoring.
• Solid Python skills, with the ability to explain and defend your design choices in code.
• Comfortable using Git for collaboration, including opening pull requests on GitHub and reviewing code, and able to read code written in Java.
• Demonstrated experience working with engineering teams on services.
• Experience with large datasets and processing technologies such as Hadoop, Spark or SQL.
• Familiarity with anomaly detection, supervised and unsupervised learning, and real-time data analysis.
• Experience with statistical analysis and strong presentation skills to turn insight into action.
• A strong product mindset and the ability to work independently across teams and functions.
• Clear communication, including explaining ideas to non-technical people.
• Strong problem-solving skills, including helping shape unclear problems and working out how to solve them.
• Formal qualifications matter less than strong experience and the ability to articulate your thinking.
• Extra skills that are great but not essential:
• Experience with MLOps tools such as Airflow, MLflow, AWS SageMaker, AWS S3, AWS EMR or CI/CD.
• Prior fraud domain experience and a solid grasp of fraud detection techniques.
• Experience designing and deploying LLM-based solutions in production.

Conditions

Hybrid working model, allowing work from home or from overseas, with flexibility for family events and personal admin.

The company welcomes applicants from all backgrounds and especially encourages applications from under-represented groups.

Benefits

• Stock options in a profitable company.
• An annual personal development budget for books, courses or conferences.
• Visa and relocation support.
• A full benefits package is available beyond these highlights.