Senior ML Engineering Team Lead - Financial Crime

Description

The company is a global technology business for moving and managing money across borders, including sending money abroad, spending abroad and receiving international payments.

It protects millions of customers and billions in transactions from fraud, money laundering and other financial crime, and its ML models are the first line of defence, serving 100K requests per minute under sub-50ms latency SLAs.

The company needs a senior technical leader to decide how these models are engineered, shipped and scaled.

Your remit is the engineering side of Risk Modelling, a pillar within the FinCrime organisation's Risk ML group, which also includes Feature Platform and Learning Loop.

You will own the full model lifecycle standard for financial crime detection, from offline experimentation through production deployment to real-time monitoring, and build the team that delivers it.

The aim is an automated engineering ecosystem and organisation that can safely scale to hundreds of models.

This is a greenfield leadership role with strong investment and engagement from the CTO and senior leadership.

Responsibilities

• Design a declarative pipeline that turns a configuration file into a deployed, monitored model, as the base for scaling to hundreds of models.
• Create a repeatable route from research, worked on with DS Research, into high-throughput production for both classical and modern architectures.
• Build infrastructure for automated retraining, drift detection, threshold simulation and management, and audit trails.
• Recruit, lead and mentor a top-tier group of ML engineers, building an engineering-first culture from scratch.
• Set hiring standards, the technical bar and career growth paths.
• Lead a team of Senior ML Systems Engineers and Applied ML Engineers.
• Own engineering strategy end to end, covering architecture, infrastructure, hiring, team culture and cross-platform work.
• Decide what to build versus consume for your pillar and manage the partnership with key platform teams.

Requirements

• You have led or built an ML engineering or model lifecycle automation team at a high-growth company, and set the standards other engineering teams followed.
• You can design a model factory architecture, review a training pipeline and debug a runtime inference latency regression.
• You have worked in high-throughput environments where latency limits are tight and model failures carry large financial consequences.
• You have hired and developed senior engineers, and built a team rather than inheriting one.
• You make architecture-level decisions with incomplete information and are comfortable with ambiguity.
• You are technically strong across deep learning, ML systems and production infrastructure, and lead through technical depth.
• You have experience at a tier-1 fintech or payments company.
• You have run graph-based methods such as GNNs or entity resolution in production.
• You have fine-tuned foundation models or evaluated LLMs.
• You have established ML engineering practices in an organisation moving from classical ML to deep learning.

Conditions

The role is hybrid.

The team works with high autonomy and low hierarchy, and you will shape direction rather than only manage delivery.

The company values diverse, equitable and inclusive teams and welcomes applicants from all backgrounds.

Benefits

• Starting salary of £135,000 to £175,000, plus RSUs.
• Access to the company's benefits package.