The company is a financial infrastructure platform for businesses. Millions of companies, from large enterprises to early-stage startups, use it to take payments, grow revenue, and open new business opportunities. Its stated goal is to raise the GDP of the internet.
The Fraud Data Science team works on merchant fraud detection, account reviews, and interventions. It works with Fraud Engineering and Risk Operations to move data science into production and to deliver measurable gains in fraud prevention. The team is also studying how AI agents can help with fraud investigations and review decisions without lowering decision quality.
Responsibilities
Set the technical direction and roadmap for Fraud Data Science, with a focus on evaluating agent-based methods for merchant fraud detection and account reviews.
Decide how to measure the quality and impact of these methods, turn findings into technical priorities, and get partners aligned on where to use them.
Balance fraud prevention, operational efficiency, and the experience of legitimate users when making decisions, using sound science and practical judgment.
Map out where data science can do the most good across merchant fraud detection, account reviews, and interventions.
Lead cross-functional work with Fraud Engineering, Risk Operations, Product, and other partners, turning unclear fraud problems into concrete technical plans with measurable results.
Build evaluation frameworks for AI agents used in fraud investigations and account reviews, covering datasets, quality metrics, offline tests, and online experiments.
Use reviewer feedback and business results alongside model and agent evaluations to find failure modes, guide iteration, and support deployment decisions.
Stay hands-on in machine learning, statistical modeling, experimentation, and measurement, guiding teams from research through to production.
Design ways to measure the effect of fraud interventions, weighing fraud losses, review efficiency, and friction for legitimate users against each other.
Turn technical findings into recommendations that shape priorities and investment across teams.
Set higher standards for evaluation, reproducibility, and production monitoring, and mentor data scientists on their technical and professional growth.
Own complex projects from problem definition through modeling, implementation, and evaluation, staying close to analysis, code, and model work and working with engineers on production deployment.
Requirements
You need to meet the minimum requirements to be considered. If you do, you are encouraged to apply. Preferred qualifications are a bonus, not a requirement.
Minimum requirements:
10+ years of data science experience, or the equivalent in combined industry and research work in a quantitative field.
A bachelor's, master's, or PhD in a quantitative field such as Statistics, Mathematics, Economics, Operations Research, Physical Sciences, or Engineering.
Experience applying data science or machine learning to fraud detection, risk decisioning, or closely related adversarial problems.
A record of leading work across several teams, or using deep domain knowledge to shape roadmap planning and delivery.
Strong grounding in machine learning and statistics, with experience designing rigorous evaluations and turning results into production or business decisions.
A proven ability to get technical and nontechnical stakeholders aligned on unclear, complex problems and to deliver measurable business results.
Ability to balance speed of execution with research depth, statistical rigor, and scalable design.
Proficiency in SQL and in a programming language such as Python or R.
Proficiency with AI tools to speed up model development, analysis, and coding.
Experience mentoring peers and investing in their growth.
Preferred qualifications (bonus, not required):
Experience with merchant fraud detection, account reviews, or fraud interventions in payments or financial services.
Experience evaluating or deploying large language model systems, including AI agents, with attention to reliability, failure analysis, and human oversight.
Experience building evaluation datasets and quality metrics for complex decisions where ground truth is incomplete or arrives late.
Experience taking machine learning or statistical systems from early research through production deployment, monitoring, and iteration.
Experience designing experiments or using causal inference to measure the impact of risk policies, review processes, or interventions.
About the company
Hidden companyCompany hidden
Industry: FinTech
Good
Your chances
Likely still hiring, not crowded yet, and you'd be among the first.
15 checks run
4 good signs
1 red flag
Still hiring?
10 checks
Likely active
StaleHiring
In its favour2
Still on the company's own careers site, checked 1 h agoModerate evidence
Found in the last 48 hours, before the big job boardsModerate evidence
Against it1
Vague on the basics: no salary, place or contract statedModerate evidence
How crowded?
5 checks
Low
QuietCrowded
In its favour2
In its Early Window: not on the big job boards yetStrong evidence
Asks for 10+ years: a narrow poolModerate evidence
?
Fits Me
How well does this role fit you?
Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.