Manager, Data Science and Machine Learning (Risk and Fraud)

Manager, Data Science and Machine Learning (Risk and Fraud) WHO WE ARE At Trustly, we're building a smarter, faster, and more secure financial future by revolutionizing the world of payments. As a global leader in Open Banking Payments, we are establishing Pay by Bank as the new standard at checkout, providing unparalleled freedom, speed, and ease to millions of consumers and merchants worldwide. Our Ambition: To build the world’s most disruptive payment network and redefine what the payment experience should feel like. Trustly is a global team of innovators, collaborators, and doers. If you are driven by a strong sense of purpose and thrive in a dynamic, entrepreneurial, and high-growth environment, join us and be part of a team that’s transforming the way the world pays. About the team The Data team at Trustly is the backbone of our decision-making and product innovation. We are a global, multidisciplinary collective of Software Engineers, Data Engineers, Machine Learning Specialists, Scientists, and Analysts who believe that data is more than just rows and columns - it is the fuel for a more transparent financial ecosystem. We operate at the intersection of high-scale engineering and deep financial intelligence. Our team processes millions of transactions in real time, turning complex Open Banking signals into seamless payment experiences. We pride ourselves on a culture of intellectual curiosity, technical excellence, and extreme ownership. About the role You will lead the team responsible for building and deploying the machine learning models at the heart of Trustly’s transaction decisioning—determining whether each transaction is approved and guaranteed. Your work will directly influence how we manage risk, prevent fraud, protect our customers, and deliver fast, reliable payment experiences at scale. This is a hands-on leadership role. You will develop and ship production-ready models yourself while setting the technical direction for a team of data scientists and machine learning engineers. You will mentor and grow the team, establish strong modeling and experimentation practices, and take end-to-end ownership of its work—from roadmap and development through deployment, monitoring, and continuous improvement. You will partner closely with Risk, Product, Engineering, and Finance to translate complex risk challenges into practical machine learning solutions and measurable business outcomes. What You Will Do Build and Ship Models Build, validate, deploy, and continuously improve machine learning models for ACH return risk, fraud detection, and account takeover. Develop real-time, online, and offline features using transaction, account, device, network, and behavioral data. Design models that operate reliably in a low-latency, high-volume production environment. Design and analyze experiments to measure the impact of model and policy changes, including champion-challenger tests, holdouts, and staged rollouts. Quantify the impact of model changes across loss rates, approval rates, customer experience, merchant performance, and overall return on investment. Translate complex modeling results into clear insights and recommendations for nontechnical partners across Risk, Product, Finance, and the broader business. Lead and Develop the Team Mentor and develop a team of full-stack data scientists and machine learning engineers with strengths across both modeling and production engineering. Hire, assess, and level talent based on technical depth, business judgment, and the ability to build reliable production systems. Set a high bar for technical quality, execution, and accountability across the team. Take ownership of what the team delivers—what ships, when it ships, and how it performs in production. Own the model roadmap across ACH return risk, fraud, and account takeover, ensuring the team focuses on the highest-impact opportunities. Establish the team’s operating cadence, including prioritization, model reviews, launch readiness, performance reviews, and postmortems following material loss events. Create an environment where the team can move quickly while maintaining strong standards for testing, documentation, governance, and production reliability. Own production model performance, including monitoring, drift detection, retraining schedules, model updates, and decisions about when a model should be modified or removed from service. Govern, Influence, and Partner Maintain comprehensive model documentation, validation evidence, decision records, and audit trails while supporting independent model validation. Ensure production decisions are explainable, with clear reason codes available when an outcome must be justified to a merchant, internal reviewer, regulator, or auditor. Partner with Product and Engineering on scoring latency, feature availability at decision time, system reliability, and integration with Trustly’s risk engine. Co-own the decision strategy and policy layer with Risk Operations, ensuring models translate into effective operational and business outcomes. Evaluate and clearly communicate the tradeoffs between approval rates, fraud and loss rates, customer experience, and revenue when recommending changes. Co-own loss forecasting with Finance and Risk, connecting model behavior and portfolio trends to financial outcomes. Present model performance, loss drivers, emerging risks, and roadmap tradeoffs to senior and executive stakeholders. Evaluate third-party risk data, tools, and model providers, determining where external capabilities can strengthen Trustly’s decisioning ecosystem. What We Are Looking For At least five years of experience building and deploying machine learning models in production, including two or more years leading a team. A genuinely hands-on technical background, with the current ability to build, validate, and deploy a production model. Strong Python skills and advanced SQL experience working with large datasets using a distributed processing engine or cloud data warehouse such as Athena, Trino, Spark, Redshift, Snowflake, or BigQuery. Direct experience in fraud, credit risk, or payments risk, including rare-event modeling, delayed labels, reject inference, and understanding the difference between a model with a strong AUC and a model that produces effective business decisions. Experience with real-time inference and production model monitoring in a low-latency decisioning environment, including drift detection, retraining strategies, and model updates. Experience owning or materially contributing to a loss budget or loss forecast, with the ability to translate model behavior into financial impact for executives, finance partners, and auditors. Strong experiment-design experience for model and policy changes, including champion-challenger testing, holdouts, staged rollouts, and rigorous measurement of results. Demonstrated experience mentoring and developing data scientists and machine learning engineers. Strong communication and stakeholder-management skills, with the ability to explain complex technical concepts, decisions, and tradeoffs clearly to nontechnical audiences. Preferred Qualifications A bachelor’s degree in a quantitative discipline such as statistics, mathematics, computer science, economics, engineering, or operations research. Proficiency with pandas and machine learning libraries such as scikit-learn, XGBoost, LightGBM, or CatBoost. Knowledge of ACH or EFT payment systems, including NACHA return codes, return behavior, and return economics. Experience working with open-banking or bank-transaction data. Experience with a cloud machine learning platform such as Databricks, AWS SageMaker, or Google Cloud Vertex AI. Experience with feature stores, streaming feature computation, real-time data pipelines, or rules and decisioning platforms. Experience applying sequence or graph-based models to behavioral or transaction data, such as recurrent architectures or entity-link analysis used to identify