Senior ML Platform Engineer II - Financial Crime

Google Chrome Microsoft Edge Apple Safari Mozilla Firefox Senior ML Platform Engineer II - Financial CrimeFull-time Compensation: GBP 111000 - GBP 145000 - yearlyCompany DescriptionWise is a global technology company, building the best way to move and manage the world’s money. Min fees. Max ease. Full speed.Whether people and businesses are sending money to another country, spending abroad, or making and receiving international payments, Wise is on a mission to make their lives easier and save them money.As part of our team, you will be helping us create an entirely new network for the world's money. For everyone, everywhere.More about our mission and what we offer.Job DescriptionAbout the role:Wise is one of the fastest-growing global financial platforms, and as we scale, so does the sophistication of the ML systems protecting every transaction. Our Risk ML team is building the model lifecycle platform that makes it possible to develop, deploy, and monitor ML models for financial crime detection - reliably, reproducibly, and at scale.We're looking for a Senior ML Platform Engineer to build this platform from the ground up. You'll design the infrastructure that turns model development from a bespoke, manual process into a scalable, standardised one - so our data and applied scientists can focus on improving detection rather than managing operations.This is a greenfield build with strong investment and direct engagement from Wise's senior leadership.How we work:Risk ML sits within Wise’s FinCrime organisation, owning the full ML and AI foundation for financial crime detection. We're scaling into three dedicated pillars - Feature Platform, Learning Loop, and Risk Modelling. You'll sit in Risk Modelling, building the platform layer that makes scaling our detection capabilities possible.You’ll work closely with data scientists, feature platform engineers (upstream infrastructure), and Wise's central ML platform team (shared foundations). We value engineers who build for adoption - internal platforms succeed when teams want to use them.What will you be working on?Designing and building the declarative training pipeline - standardised, config-driven model training that any data scientist can use without writing deployment codeBuilding model packaging and serving abstraction - a unified interface that handles multiple model types (classical ML, deep learning, emerging architectures) through a consistent APIImplementing the model evaluation framework - standardised metrics, reproducible comparison, and automated validation gatesBuilding model monitoring - drift detection, performance degradation alerts, automated retraining triggers, and full audit trails for regulatory complianceOwning the integration layer with Wise's central ML infrastructure - aligning on boundaries so FinCrime-specific lifecycle tooling builds cleanly on shared foundationsMaximising data science productivity - your platform's success is measured by how much time shifts from operational maintenance to improving detection performanceWhat do you need?Experience building ML platform infrastructure in production - training pipelines, model serving, evaluation frameworks, or monitoring systems. Infrastructure that other teams depend on, not individual model work.Strong software engineering fundamentals - you build reliable, well-tested, maintainable systems. Python, Kotlin/Java, SQL.Experience with ML orchestration (Airflow, Kubeflow, or equivalent), model registries (MLflow or similar), and container-based deploymentEnd-to-end understanding of the ML lifecycle - data ingestion through training, packaging, serving, and monitoring - and knowledge of where things breakA product mindset for internal tooling - you think about data scientists as users and build for adoption, not just functionalityNice to Have:Model serving at scale - latency optimisation, ONNX packaging, canary deployments for modelsExperience in FinCrime, fraud, AML, or regulated...