Senior Data Scientist, Fraud Prevention

GoCardless
Riga, Latvia€64k – €96kPosted 27 February 2026

Job Description

<div class="content-intro"><h3><strong>About Us at GoCardless</strong></h3> <p>GoCardless is a <strong>global bank payment</strong> company. Over <strong>100,000 businesses</strong>, from start-ups to household names, use GoCardless to collect and send payments through direct debit, real-time payments and open banking. </p> <p>GoCardless processes <strong>US$130bn+</strong> of payments annually, across <strong>30+ countries</strong>; helping customers collect and send both <strong>recurring</strong> and <strong>one-off payments</strong>, without the chasing, stress or expensive fees. We use AI-powered solutions to improve payment success and reduce fraud. And, with open banking connectivity to over <strong>2,500 banks</strong>, we help our customers make faster, more informed decisions.</p> <p>We are headquartered in the<strong> UK</strong> with offices in <strong>London</strong> and <strong>Leeds</strong>, and additional locations in <strong>Australia, France, Ireland, Latvia, Portugal</strong> and the <strong>United States.</strong></p> <p>At GoCardless, we're all about <strong>supporting you</strong>! We’re committed to making our hiring process <strong>inclusive</strong> and <strong>accessible</strong>. If you need extra support or adjustments, reach out to your <strong>Talent Partner</strong> — we’re here to help! </p> <p>And remember: we don’t expect you to meet every single requirement. If you’re excited by this role, <strong>we encourage you to apply!</strong></p></div><h3>The role</h3> <p>This role will be working within the Fraud Prevention team in our Merchant Operations Group. The Fraud Prevention team plays a critical role in protecting the integrity of the GoCardless platform by building systems that prevent and detect merchant fraud before it impacts our business or our customers. </p> <p>The Fraud Prevention Data Scientist will work closely with Engineers and Fraud Analysts to develop and deploy predictive models that strengthen our fraud defenses. You’ll focus on the end-to-end delivery of ML solutions - from feature engineering and prototyping to production-grade deployment - to reduce false positives and automate controls without introducing unnecessary friction. You’ll also collaborate with cross-functional stakeholders to ensure our ML products scale on our GCP stack, driving fintech innovation while supporting a seamless customer experience.</p> <h3><strong>What you’ll do</strong></h3> <ul> <li>Contribute to the end-to-end delivery of models at scale, from initial discovery and feature engineering to production, A/B testing and continuous monitoring.</li> <li>Collaborate with product, engineering and data science peers to turn complex data into real-time, mission-critical fraud prevention solutions.</li> <li>Raise the team’s collective bar through hands-on technical leadership and knowledge sharing.</li> <li>Help bring to live the latest developments in ML and payer fraud prevention to drive innovation at GoCardless.</li> </ul> <h3><strong>What excites you</strong></h3> <ul> <li>Being a self-starter who thrives on taking a vague business problem and owning the journey from the first prototype to a live, measurable solution.</li> <li>Contributing to the future of fraud prevention, by shaping up the data and ML products all the way from the initial insights to the market-ready solutions.</li> <li>Working with a range of stakeholders to discover and design ML solutions, adapting them to the markets as we grow.</li> <li>Building production-grade ML models on a streamlined GCP and Vertex AI stack to drive fintech innovation.</li> </ul> <h3><strong>What excites us</strong></h3> <ul> <li>You hold a degree (or PhD) in a STEM discipline or an equivalent commercial experience.</li> <li>You have a track record of deploying predictive models and data products in production with quantifiable impact (experience in Fintech, Fraud Prevention, or Payments is a big plus).</li> <li>You can translate complex ML concepts into ... (truncated, view full listing at source)