Data Scientist, Antifraud

Almaty, Kazakhstan. Posted a month ago

The role

You will own the account-abuse scoring system to distinguish between fraud and unprofitable pricing. You will build detection systems, perform entity resolution to find fraud rings, and design enforcement actions to protect compute resources.

What you will do

Own the account-abuse scoring system end to end
Build detection that fires early to catch abuse before compute is burned
Work on linkage and economics to identify connected users
Find rings using shared payment instruments, IP, ASN, and behavioral fingerprints
Design graduated and reversible enforcement actions
Own the false-positive budget
Build pre-grant gates to decline abuse at the start
Partner with Payments, Support, and Legal teams
Quantify the monetary value of the detection system
Monitor for adversarial adaptation and model decay

Required qualifications

Experience building abuse, fraud or trust-and-safety detection that took action on real users
Understanding of the adversarial setting
Strong SQL and Python on raw event data
Comfort with graph and linkage thinking
Precision-first evaluation instincts
Unit-economics literacy
Judgment to escalate rather than act when evidence is thin
Clear written and spoken English, B2+

Nice to have

Fraud / risk data scientists from fintech, payments, marketplaces, gaming or crypto
Trust & safety and platform-integrity teams who owned detection and enforcement policy
Growth or product data scientists who owned promo-abuse
Analysts from payment processors, PSPs or chargeback/dispute operations who moved into modelling

Benefits

Competitive salary in USD
Participation in the company's stock option program
Relocation support (flight + temporary housing)
Flat structure
High autonomy
Fast career growth

Before you apply

Screening call
Hiring-manager screen
Business case
Take-home with real-shaped data
Team interview

About the company

Higgsfield AI is a generative AI company building AI-powered video creation and creative tools.