Responsibilities
- Design and ship production ML and deep learning models for real-time financial crime detection.
- Define architecture strategy covering model families, training paradigms, serving patterns, and scalable risk-modeling systems.
- Build reusable end-to-end pipelines spanning experimentation, training, and production deployment.
- Evaluate foundation model and embedding approaches for transaction representation across financial crime domains.
- Partner with Data Science on model evaluation, experimentation design, and causal impact measurement.
- Mentor engineers and data scientists on ML fundamentals, production practices, and architectural decision-making.
Requirements
- Production experience shipping deep learning models at scale in systems serving real traffic under latency constraints.
- Ability to independently make and communicate architecture-level decisions involving model selection, training infrastructure, and serving strategy.
- Experience designing ML systems with demanding latency and throughput requirements, including quantization, pre-computed embeddings, and batching strategies.
- Strong fundamentals in gradient dynamics, attention mechanisms, graph message-passing, and sequence modeling.
- A track record of influencing technical strategy across teams.
- Experience with Python, PyTorch or an equivalent framework, distributed training, and ML pipeline orchestration.
- Experience in financial crime, fraud detection, anti-money laundering, or regulated financial services is preferred.
- Production experience with graph-based methods such as graph neural networks, entity resolution, or link analysis is preferred.
- Foundation model fine-tuning or large language model evaluation experience is preferred.
- Experience establishing modern ML practices in organizations scaling their ML capabilities is preferred.
Benefits
- Starting salary of £145,000–£182,000 plus RSUs.
- Hybrid work arrangement.
- Wise benefits and an international, inclusive working environment.
Categories
About Wise
Wise is a global technology company, building the best way to move money around the world. With the Wise account people and businesses can hold 40+ currencies, move money between countries and spend money abroad. Large companies and banks use Wise technology too; an entirely new cross-border payments network that will one day power money without borders for everyone, everywhere. However you use the platform, Wise is on a mission to make your life easier and save you money. Co-founded by Kristo Käärmann and Taavet Hinrikus, Wise launched in 2011 under its original name TransferWise. It is one of the world’s fastest growing, profitable technology companies and is dual listed on Nasdaq in the US (WSE) on the London Stock Exchange under the ticker, WISE. 19 million people and businesses use Wise globally. In fiscal year 2026, Wise supported around 19 million people and businesses, processing over $240 billion in cross-border transactions and saving customers over $3 billion. For customer queries: Please note that LinkedIn is not a Wise Customer Support channel. If you would like to hear from our Customer Support team, please see our Facebook, Twitter and Instagram pages. Login to access customer support: https://wise.com/login/ FB: https://www.facebook.com/Wise/ IG:https://www.instagram.com/wiseaccount/ TW:https://twitter.com/home