Staff ML Engineer — Real-Time Fraud Platform

MoonPay Inc.; Greater London; Hybrid; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Competitive salary package

Equity package

Pay-for-performance equity bonus

Moonshot award

Pension

Employee referral program

Flexible Time Off

Birthday leave

Hybrid working schedule

Commuter benefits

Private healthcare benefits

Wellhub wellness membership

AI tools access

Lunch credit

Home office setup allowance

Remote working allowance

Annual training budget

High Potential Program

Remote company offsites

Cycle to Work

EV Salary Sacrifice

Job summary

MoonPay is seeking a Staff Machine Learning Engineer to own the decisioning system and ML lifecycle. You will build, ship, and maintain real-time scoring services for fraud detection, integrating training and serving, and enabling safe, live updates in a hybrid London office.

You will lead architecture across feeding data, model deployment, and production monitoring, with emphasis on robust, scalable, low-latency systems and cross-team collaboration within a high-velocity environment.

Qualifications

• Real-time, low-latency services on critical paths.
• Holistic system design and graceful degradation.
• Robust, testable, production-grade code.
• End-to-end ML pipelines ownership from training to deployment.
• Ability to influence and ship complex projects.

Responsibilities

• Own the decisioning and serving platform for live transactions.
• Build feature infrastructure across batch, near-real-time, and in-request paths.
• Maintain alignment between training and serving for production parity.
• Develop tooling for replay, shadow, and staged rollouts.

Skills

Real-time serving

Systems thinking

Engineering craft

Pipelines in production

Ambiguity and influence

Tools

GCP

BigQuery

Bigtable

Memorystore

Vertex AI

Kubernetes

Job description

MoonPay is seeking a Staff Machine Learning Engineer to own the decisioning system and ML lifecycle. You will build, ship, and maintain real-time scoring services for fraud detection, integrating training and serving, and enabling safe, live updates in a hybrid London office.

You will lead architecture across feeding data, model deployment, and production monitoring, with emphasis on robust, scalable, low-latency systems and cross-team collaboration within a high-velocity environment.