Senior Real-Time ML Engineer: Fraud Platform Lead

Inflection Managing Partner, Inc.; Greater London; Hybrid; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Competitive salary

Equity package

Performance equity bonus

Moonshot equity grant

Pension contributions

Referral program

Flexible time off

Hybrid working

Commuter benefits

Private healthcare

Wellhub wellness

AI tools access

Lunch stipend

Home office setup

Remote working allowance

Annual training budget

High Potential Program

Offsites

EV Salary Sacrifice (UK)

Job summary

MoonPay in London is seeking a Staff Machine Learning Engineer to own the real-time decisioning platform for fraud prevention, covering the full lifecycle from training to deployment and monitoring.

You will build and operate high-availability services with strict latency budgets, ensure production models match offline expectations, and scale the platform as volume grows while fostering robust feedback loops.

Qualifications

• Must-have experience building and operating low-latency services.
• Holistic systems thinking and robust feedback loops.
• Strong engineering craft with tested, typed code.
• End-to-end feature/data pipelines ownership.
• Ability to lead and influence others in ambiguous contexts.

Responsibilities

• Own real-time decisioning services for in-flight transactions.
• Scale platform as volume and model complexity grow.
• Maintain alignment between training and serving in production.
• Implement safe, reversible model deployment practices.

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 in London is seeking a Staff Machine Learning Engineer to own the real-time decisioning platform for fraud prevention, covering the full lifecycle from training to deployment and monitoring.

You will build and operate high-availability services with strict latency budgets, ensure production models match offline expectations, and scale the platform as volume grows while fostering robust feedback loops.