Profile cover
C

AI Payment Fraud Network Graph Analyst

Ilvix Works

Remote · $130k – $160k / year · Full-time · Posted 4 months ago

No longer accepting applications

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Individual transaction fraud models are good at catching individual fraudsters. They're bad at catching fraud rings — coordinated networks where individual transactions look legitimate but the network pattern reveals the scheme. A ring of 300 synthetic identities sharing address components, device fingerprints, and referral codes is nearly invisible to per-transaction models. A graph neural network sees it immediately. We process $8B in payment volume per month and lose $14M annually to organized fraud rings that our current models miss. We've built the graph: 12 million nodes (accounts, devices, addresses, cards, merchants) and 90 million edges updated in near-real-time. We haven't built the intelligence layer that turns that graph into fraud signals. You'll own this capability. Design the graph ML models, build the feature engineering on top of the payment network graph, integrate the fraud signals into our existing decision engine, and define the monitoring that tracks ring detection accuracy as fraudsters adapt. This is high-stakes work: every percentage point improvement in ring detection precision saves roughly $140K per month.

Fully remote.

Responsibilities

  • Design graph neural network models for payment fraud ring detection
  • Build graph feature engineering from the 12M-node, 90M-edge payment network
  • Integrate ring detection signals into the existing real-time decision engine
  • Develop adversarial robustness — fraudsters adapt, models must adapt faster
  • Build monitoring that tracks ring detection accuracy against confirmed fraud cases
  • Collaborate with the fraud operations team to validate newly detected ring patterns

Requirements

  • 6+ years in ML engineering with fraud detection or financial crime experience
  • Hands-on experience with graph neural networks in production
  • Strong Python, Spark, and SQL skills for large-scale graph data processing
  • Deep understanding of payment network structures and fraud patterns
  • Track record delivering measurable fraud loss reduction

Benefits

  • Fully remote with flexible schedule
  • Comprehensive health benefits
  • $4,000 annual professional development budget
  • Equity participation
  • Bonus tied to fraud loss reduction metrics

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

AI & Machine Learning Engineers Data Science & Analytics

Skills

python pytorch spark sql statistics

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Principal Engineer Team Lead, Behavior Safety & Metrics

Motional

Full-time Principal

Sr Technical Program Manager, Data

Hyperscience

Full-time Senior

Materials Lead

Lambda

Full-time Lead

Senior Data Engineer, Data Analytics

Agility Robotics

Full-time Senior

Lead/ Senior Machine Learning Scientist, Integrative Phenotyping

insitro

Full-time Lead

Software Engineer, Developer Products

OpenRouter

Full-time

Job Type

Full-time

Level

Senior

Language

English

Salary Range

$130k – $160k / year

AI Expertise

AI & Machine Learning Engineers Data Science & Analytics

Skills

python pytorch spark sql statistics pandas

Ready to apply for this role?

Create a free talent account.

  • Find AI roles in one place
  • Get AI-matched job recommendations
  • Reply to companies that message you
  • Build your public AI talent profile
Create free account & apply Log in

This role is closed. Create your free profile to apply to similar open roles.

Don't miss the next one: get matched to new roles like this.

Create free profile