Staff Analyst - Risk and Fraud Systems

The role

This role builds data, decision and automated systems that reduce fraud losses and manual work while letting Paddle accept more good risk. The work is hands-on, using SQL, Python and statistics, and covers seller risk controls, fraud case libraries and production monitoring.

What you will do

• Work hands-on with SQL (Snowflake, dbt), Python and statistics to explore data, test hypotheses and prototype controls.
• Map the end-to-end seller risk system, including its data, decisions, controls, owners and failure points.
• Establish a baseline of fraud losses, alert yield, time-to-detect, exposure at detection and analyst effort.
• Own the health of live controls, with owners, expected volumes, measured yield and alerts when controls drift.
• Build and maintain a labelled library of confirmed fraud cases and a shared fraud typology.
• Build a value-ranked portfolio of risk opportunities.
• Translate risk problems into product, data and engineering work with measurable acceptance criteria.
• Design seller risk tiers that set payout timing, reserves and limits.
• Backtest rules and risk scores on point-in-time data and design experiments and phased roll-outs.
• Produce decision artefacts that help senior leaders make trade-offs about risk appetite and investment.

Required qualifications

• Significant experience building or improving merchant- or seller-side fraud detection at a PSP, acquirer, payfac, marketplace or Merchant of Record.
• Working knowledge of how bust-out, transaction laundering and self-dealing show up in the data.
• Strong hands-on analytical ability with fluency in SQL (Snowflake, dbt or similar), Python and statistics.
• Experience using LLMs on unstructured data such as website content or support tickets, with measured accuracy.
• Experience working with decision flow systems such as Tactile.
• A record of turning ambiguous cross-functional problems into adopted systems with measurable results.
• Experience designing, backtesting and tuning rules and risk scores on point-in-time data with delayed, partial and adversarial labels.
• A habit of treating controls as production systems, with version control, testing, impact analysis, monitoring and audit trails.
• Ability to put risk trade-offs in money using a method Finance will sign off.
• Good judgement about when a problem needs a rule, workflow, experiment, vendor, model or agent.
• Ability to work credibly with investigators, operators, product managers, engineers, data scientists and executives.
• Comfortable challenging inherited assumptions while keeping the people closest to the work involved.

Nice to have

• Experience in a Merchant of Record, payments, marketplace, subscription or other adversarial transactional environment.
• More interested in solving and shipping than in building an empire.

Benefits

• Attractive salaries
• Stock options
• Unlimited holidays
• Enhanced parental leave
• Retirement plans
• Private healthcare
• Well-being initiatives
• Annual learning fund
• Regular internal and external training
• Digital-first flexible working

Before you apply

• Paddle encourages applications even if you do not match every part of the job ad.

About the company

Paddle is a Merchant of Record that handles payment infrastructure for digital product companies. It serves over 10,000 software sellers in 245 territories and is backed by investors including KKR, FTV Capital, Kindred, Notion and 83North.