Source Job

• Define the technical strategy and roadmap for credit risk and fraud detection using statistical and ML approaches.
• Design, build, and deploy production-quality machine learning models for credit scoring, fraud detection, and risk modeling.
• Collaborate closely with Engineering, Product, Risk, and Operations teams to align data science strategy with business goals.

Djamo builds the future of banking in Africa with a super-app that combines payments, transfers, savings, and budgeting. Launched in 2020, the company serves over one million users and is backed by investors like Y Combinator and Partech, fostering a culture of innovation and inclusion.

• Work directly with TelCo clients to uncover emerging fraud trends and co-build detection models using cross-industry data.
• Translate ambiguous client questions into clear analytical plans and execute them independently from start to finish.
• Build reusable tools, templates, and analytical frameworks to scale the fraud analytics consortium offering.

Experian is a global data and technology company that redefines lending, prevents fraud, simplifies healthcare, and creates digital marketing solutions across multiple industries. As a FTSE 100 company with 23,300 employees across 32 countries, they prioritize innovation, inclusion, and a people-first culture.

• Develop, validate, and optimize statistical and machine learning models including regression and XGBoost to detect and prevent fraud.
• Design features, build tools, and deploy models in production environments to improve performance and stability.
• Conduct model governance activities including validation, documentation, and ongoing monitoring with clear reporting.

Experian is a global data and technology company powering opportunities for people and businesses worldwide, operating across financial services, healthcare, automotive, and more. With 23,300 employees in 32 countries, the company is a FTSE 100 Index listed firm recognized for its people-first culture and advanced technology investments.

• Design and execute structured evaluation frameworks to assess the quality and fraud-signal value of incoming data assets from vendor partners.
• Build lift analyses, backtests, and champion/challenger comparisons to quantify the incremental value of new data signals against our existing fraud detection stack.
• Collaborate with fraud leadership to define evaluation criteria and translate vendor data findings into actionable recommendations such as adopt, pilot, or decline.

Sardine is the leading agentic risk platform for fighting financial crime, unifying data across risk teams to stop fraud in real time and prevent AI-driven attacks. They are a remote-first company with hubs in the Bay Area, NYC, Austin, Toronto, and São Paulo, valuing performance and self-motivated individuals.

• Design, develop and deploy advanced statistical or machine learning models for credit risk, pricing, collections, fraud, and other high-impact business use cases.
• Lead end-to-end delivery of data science initiatives from problem framing through deployment and monitoring.
• Partner with cross-functional teams including Portfolio Strategy, Engineering, Product, and Sales to integrate models and solve critical business problems.

Forward Financing is a fintech company that unlocks capital for small businesses across America. Since 2012, it has provided over $4.8 billion in funding to more than 92,000 small businesses and is recognized as a Best Place to Work by Built In Boston.

• Analyze and assess risk by examining financial data, transaction patterns, and user behavior to identify fraud, credit, and compliance risks.
• Develop and implement risk controls by partnering with product, engineering, and data science teams to build automated decisioning systems.
• Contribute to strategic planning by providing insights on risk trends and policy improvements to support company growth.

Found builds tools to give self-employed people the security of big corporations through a business bank account that automates taxes and expense tracking. The company is a growing fintech startup with a diverse team, offering a collaborative culture focused on making a meaningful impact.

• Build advanced machine learning models to detect and prevent financial crime, reducing fraud and scams.
• Work cross-functionally with product managers, data scientists, and engineers in an agile environment.
• Provide technical leadership and mentorship to drive up standards in machine learning practices.

Monzo is on a mission to make money work for everyone by offering personal and business bank accounts, savings, investments, and credit cards in the UK. With over 25 people in the Financial Crime Data team, we foster a culture of innovation and inclusivity.

• Use SQL and other analytical tools to conduct in-depth analysis of customers, transactions, alerts, and risk ratings.
• Develop, tune, and maintain transaction monitoring and sanctions screening models to improve detection and reduce false positives.
• Partner with compliance, product, and data leaders to translate regulatory requirements into effective analytical frameworks.

Mercury is building a complete finance stack for startups, providing banking services through partner banks. As a fintech company, they focus on creating a safe and easy banking experience while protecting against bad actors, with a culture of high agency and adaptability.

• Design, develop, and optimize predictive risk models and decision frameworks across payment rails and cryptocurrency domains.
• Partner with Product, Engineering, and Operations to embed model-driven risk decisioning throughout the customer journey.
• Conduct deep-dive investigations into fraud events and payment losses, supporting model governance and regulatory review.

Binance.US is a licensed and regulated U.S. crypto platform providing secure access to over 190 cryptocurrencies with low fees. It is a remote-first team of innovators building the bridge between traditional finance and Web3, committed to financial freedom for all.

• Analyze banking transactions and enhance fraud detection algorithms using graph-based analysis of financial data.
• Build and integrate ML models, including classic, graph-based, and neural network approaches, into the Fraud Protection platform.
• Document research findings and present them to stakeholders, contributing to broader graph-related tasks like GraphRAG components.

Group-IB is a leading cybersecurity technology creator dedicated to investigating, preventing, and fighting digital crime. With over 1,550 cybercrime investigations and 600+ enterprise customers globally, the company operates Digital Crime Resistance Centers across multiple regions, fostering a culture of mission-driven innovation and global collaboration.

• Develop credit and fraud strategies using data, machine learning models, and advanced analytics to optimize risk decisions.
• Design A/B tests to balance risk and customer experience, and partner with Data Science, Product, and Engineering teams.
• Analyze portfolio performance at a granular level, identify trends, and communicate findings to Risk Management.

Prosper is a fintech company that pioneered peer-to-peer lending in the US, offering personal loans and credit cards to help consumers achieve financial well-being. Since 2005, it has served over 2 million customers and fosters a culture of collaboration, curiosity, and accountability.

• Lead a high-calibre ML team to shape Borrowing's ML roadmap across UK growth, new customer segments, and EU expansion.
• Improve underwriting, pricing, limits, and lifecycle decisioning through faster model iteration and new data sources.
• Partner with leaders across Credit Strategy, Product, Engineering, and Data to drive commercial impact and long-term strategic advantage.

Monzo is on a mission to make money work for everyone, offering personal and business bank accounts, savings, investments, and pensions. As a rapidly growing fintech with a strong UK presence, we foster an inclusive culture focused on innovation and customer delight.

• Design, build, and maintain scalable machine learning infrastructure on AWS, including training and deployment pipelines.
• Develop and deploy ML models for recommendation systems, fraud detection, credit risk, and personalization use cases.
• Implement monitoring, logging, and alerting systems to ensure model performance, stability, and reliability in production.

Our partner is a fast-growing, innovation-driven company where machine learning and AI systems directly power large-scale fintech and commerce experiences. They foster a highly dynamic environment with strong emphasis on experimentation, rapid iteration, and measurable business impact.