Senior ML Platform Engineer II - Financial Crime

• Build the ML model lifecycle platform from the ground up for Wise's financial crime detection — a greenfield build with strong investment and direct engagement from senior leadership. • Design the infrastructure that turns model development from a bespoke, manual process into a scalable, standardised one so data and applied scientists can focus on improving detection. • Sit within the Risk Modelling pillar of Wise's FinCrime organisation, owning the full ML and AI foundation for financial crime detection. • Work hybrid from Wise's London office.

• Have experience building ML platform infrastructure in production — training pipelines, model serving, evaluation frameworks, or monitoring systems that other teams depend on, not individual model work. • Bring strong software engineering fundamentals — build reliable, well-tested, maintainable systems in Python, Kotlin/Java, and SQL. • Have experience with ML orchestration such as Airflow, Kubeflow, or equivalent, model registries like MLflow or similar, and container-based deployment. • Have an end-to-end understanding of the ML lifecycle — data ingestion through training, packaging, serving, and monitoring — and know where things break. • Have a product mindset for internal tooling — think about data scientists as users and build for adoption, not just functionality.

• Have experience with model serving at scale including latency optimisation, ONNX packaging, and canary deployments for models. • Bring experience in FinCrime, fraud, AML, or regulated environments where audit trails and model governance are non-negotiable. • Have experience with model monitoring and drift detection systems in production. • Have a track record of migrating teams from manual ML workflows to platform-based approaches.

• Design and build the declarative training pipeline — standardised, config-driven model training that any data scientist can use without writing deployment code. • Build model packaging and serving abstraction — a unified interface handling multiple model types through a consistent API. • Implement the model evaluation framework — standardised metrics, reproducible comparison, and automated validation gates. • Build model monitoring — drift detection, performance degradation alerts, automated retraining triggers, and full audit trails for regulatory compliance. • Own the integration layer with Wise's central ML infrastructure, aligning on boundaries so FinCrime-specific lifecycle tooling builds cleanly on shared foundations. • Maximise data science productivity — the platform's success is measured by how much time shifts from operational maintenance to improving detection performance.

We have been Wise customers for years and have always had a great experience. We love their transparent approach in everything they do, from showing the correct exchange rates to disclosing all their fees, and even being honest about how they work. Founded in 2010 in London, Wise is now a publicly traded company operating in over 160 countries, generating 1.2+ billion pounds in revenue (2025) and is highly profitable. What we especially love at Wise is their work from anywhere policy after 6 months: Basically you can remotely work from (almost) anywhere in the world for up to 90 days a year. As they are solving a massive problem and are strongly mission-driven, we are sure that any individual passionate about working on complex, impactful problems in sending money globally efficiently, while continuing to work on the much-loved Wise solutions, will love working there.

• Earn £111,000–£145,000 plus RSUs. • Build an ML platform from the ground up with strong investment and direct engagement from Wise's senior leadership. • Work within a FinCrime organisation scaling into three dedicated pillars — Feature Platform, Learning Loop, and Risk Modelling. • Join a global technology company building the best way to move and manage the world's money.

Wise is a global technology company building the best way to move and manage the world's money. 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. The Risk ML team sits within Wise's FinCrime organisation, owning the full ML and AI foundation for financial crime detection and scaling into three dedicated pillars: Feature Platform, Learning Loop, and Risk Modelling.