Staff Applied ML Engineer - Financial Crime

Google Chrome Microsoft Edge Apple Safari Mozilla Firefox Staff Applied ML Engineer - Financial CrimeFull-time Compensation: GBP 145000 - GBP 182000 - 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 moves billions across borders every year. Behind every transaction is a decision: is this safe? Our ML systems make that call - at scale, in real time, across every market we operate in.Our Risk ML team is building the next generation of financial crime detection at Wise - investing in modern architectures like deep learning, graph neural networks, and foundation models to detect increasingly sophisticated fraud and money laundering patterns. We're looking for a Staff Applied ML Engineer to lead this evolution: defining the architecture strategy, shipping production neural models, and building the blueprint that scales across FinCrime domains.This is a greenfield opportunity - you'll be setting the direction for how Wise applies modern ML to financial crime risk, with strong investment and engagement from 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, working alongside data scientists, platform engineers, product and domain experts.We operate with high autonomy and low hierarchy. You'll own problems end-to-end - from research and architecture decisions through to production deployment and impact measurement. We value engineers who shape direction, not just execute tickets.What will you be working on?Designing and shipping ML and deep learning models for financial crime detection - sequence-based, graph-based, attention-based - serving real-time decisions at Wise's scaleDefining the architecture strategy for how Wise applies modern ML to risk - which model families, which serving patterns, which training paradigmsBuilding the reusable end-to-end pipeline pattern - from experimentation through training to production deployment - that future models followEvaluating and prototyping foundation model and embedding approaches for transaction representation across FinCrime domainsPartnering with Data Science on model evaluation, experimentation design and causal measurement in domains where clean A/B testing isn't always possibleMentoring engineers and data scientists on modern ML fundamentals, production best practices, and architectural decision-makingWhat do you need?Production experience shipping deep learning models at scale - systems serving real traffic under latency constraintsAbility to make architecture-level decisions independently - model selection, training infrastructure, serving strategy - and explain the reasoning and tradeoffsExperience designing ML systems with hard latency and throughput requirements, including optimisation decisions (quantization, pre-computed embeddings, batching strategies)Strong fundamentals in deep learning: gradient dynamics, attention mechanisms, graph message-passing, sequence modellingTrack record of influencing technical strategy across teams - you don't just build, you shape directionPython, PyTorch (or equivalent), distributed training, ML pipeline orchestrationNice to Have:Experience in FinCrime, fraud detection, AML, or regulated financial servicesExperience with graph-based methods (GNNs, entity resolution, link analysis) in productionFoundation...