Staff Applied ML Engineer - Financial Crime

Responsibilities

• Design and ship production-scale deep learning models (sequence-based, graph-based, attention-based) for real-time financial crime detection
• Define the architecture strategy for modern ML application at Wise, including model families, serving patterns, and training paradigms
• Build reusable end-to-end ML pipeline patterns from experimentation through to production deployment
• Evaluate and prototype foundation model and embedding approaches for transaction representation
• Partner with Data Science on model evaluation, experimentation design, and causal measurement
• Mentor engineers and data scientists on modern ML fundamentals and architectural decision-making

Requirements

• Production experience shipping deep learning models at scale under strict latency and throughput constraints
• Ability to make independent, architecture-level decisions regarding model selection, training infrastructure, and serving strategy
• Strong fundamentals in deep learning, including gradient dynamics, attention mechanisms, and sequence modelling
• Proficiency in Python and PyTorch (or equivalent)
• Experience with distributed training and ML pipeline orchestration
• Proven track record of influencing technical strategy across multiple teams

Preferred Qualifications

• Experience in FinCrime, fraud detection, AML, or regulated financial services
• Experience with graph-based methods (GNNs, entity resolution, link analysis) in a production environment
• Experience with foundation model fine-tuning or LLM evaluation
• Experience establishing modern ML practices within scaling organizations

Benefits

• Competitive salary: £145,000 - £182,000
• Restricted Stock Units (RSUs)
• Comprehensive Wise benefits package

About the Company

Wise is a global technology company on a mission to make moving money across borders instant, convenient, transparent, and much cheaper. We are building a new network for the world's money, designed for everyone, everywhere.