• Build industry-leading machine learning models for managing credit and fraud risks • Leverage multiple complex data sources such as credit bureau reports and customer supplied information at large scale • Collaborate with engineers to deploy your models into a production environment • Propose and execute solutions to various problems within business constraints • Use responsible AI technique following regulatory requirements and lending best practices • Actively monitor the credit risk models in production • Extract the most value out of data to significantly impact our key business metrics • Conduct ad-hoc analysis related to risk management, investor services, operations and corporate development

• Work independently with cross functional teams to develop software and system requirements. • Design, implement, and deploy state-of-the-art machine learning models. • Monitor the performance of the ML models and drive continuous improvement. • Lead team code quality activities including design and code reviews. • Communicate complex analytical findings and model performance metrics to both technical and non-technical stakeholders through clear visualizations and presentations. • Provide technical guidance to team members.

• Engaging with sales leads as a “human explicability layer,” up-leveling understanding for non-technical audiences to ensure that complex underwriting results are communicated clearly to drive sales. • Leading complex and dynamic collaborations between the Data Science and Growth teams. • Helping us refine the competitiveness of our value-based care contracts. • Ensuring quality and availability of various data sources. • Leveraging a deep understanding of ML concepts (e.g., using SHAP or feature importance but also less formal quantitative instinct) to consult on the application of payment models. • Designing and engineering analytics tooling to stress-test our underwriting outputs. • Deepening knowledge of healthcare models. • Evaluating vendors and technologies.

• Critically analyze large health datasets using standard and bespoke software libraries • Discuss your findings and progress with internal and external stakeholders • Produce high quality reports which summarise your findings • Contribute to research activities as we explore novel and established sources of re-identification risk