• Develop statistical analyses to identify patterns, trends, and opportunities for improvement; • Build, validate, and monitor predictive models using machine learning techniques; • Work on data cleaning, exploration, and preparation of datasets; • Develop forecasting models to support planning and decision-making; • Evaluate model performance and propose continuous improvements; • Translate analytical results into business recommendations; • Collaborate with cross-functional teams to understand requirements and implement analytical solutions

• Develop novel, state-of-the-art AI and machine learning models to support risk strategies; • Recommend data-driven, risk-based business decisions to positively impact KPIs across Trustly's payment portfolio; • Conduct analysis to measure model performance, compare performance across multiple models, and influence model strategy and selection decisions; • Collaborate with ML Engineers to deploy AI/ML models and strategies in Trustly's decision engine; • Explore raw source data, perform feature research and engineering to support decisioning capabilities; • Support development and maintenance of risk modeling infrastructure, working closely with ML Engineers and MLOps; • Develop data- and business-driven risk prevention rules and strategies; • Monitor risk and decision trends and performance, providing ongoing optimization adjustments as needed.

• Act in a consultative capacity alongside business teams, understanding pain points and proposing data-driven solutions; • Lead end-to-end data science projects (from problem definition to production delivery); • Translate business problems into analytical approaches (predictive models, segmentations, optimizations, etc.); • Communicate results and insights clearly to technical and non-technical stakeholders; • Ensure the quality, reproducibility, and governance of developed models; • Communicate technical points, decisions, and trade-offs to peers and stakeholders;

• Work alongside our data migration and engineering teams on live client projects, contributing to the day-to-day delivery of healthcare data work. • Identify inefficiencies, repetitive tasks, and fragile processes - and build the scripts, tools, and small systems that fix them. • Write and maintain code, primarily in Python & SQL, to automate workflows, process data, and support internal operations. • Apply and experiment with AI tooling - LLMs, embeddings, classifiers - to problems across the business where they add real value, and be honest about where they don’t. • Communicate your work clearly, in writing and in person, to colleagues who are not data scientists - so that your improvements get adopted rather than sidelined. • Over time, contribute to Stalis’s emerging data science and machine learning capability, including schema mapping, clinical data analytics, and data products.