Data Scientist Department: Detection Employment Type: Full Time Location: Remote Description Who are we? Hi! 👋 We are Ravelin! We're a fraud detection company using advanced machine learning and network analysis technology to solve big problems. Our goal is to make online transactions safer and help our clients feel confident serving their customers. And we have fun in the meantime! We are a friendly bunch and pride ourselves in having a strong culture and adhering to our values of empathy, ambition, unity and integrity. We really value work/life balance and we embrace a flat hierarchy structure company-wide. Join us and you’ll learn fast about cutting-edge tech and work with some of the brightest and nicest people around - check out our Glassdoor reviews. If this sounds like your cup of tea, we would love to hear from you! For more information check out our blog to see if you would like to help us prevent crime and protect the world's biggest online businesses. The Team You will be joining the Detection team. The Detection team is responsible for keeping fraud rates low – and clients happy – by continuously training and deploying machine learning models. We aim to make model deployments as easy and error free as code deployments. Google’s Best Practices for ML Engineering is our bible. Our models are trained to spot multiple types of fraud, using a variety of data sources and techniques in real time. The prediction pipelines are under strict SLAs, every prediction must be returned in under 300ms. When models are not performing as expected, it’s down to the Detection team to investigate why. The Detection team is core to Ravelin’s success. They work closely with the Data Engineering Team who build infrastructure and the Intelligence & Investigations Team who liaise with clients. The Role We are currently looking for a Data Scientist to help train, deploy, debug and evaluate our fraud detection models. Our ideal candidate is pragmatic, approachable and filled with knowledge tempered by past failures. Evaluating fraud models is hard; often times we do not even get labels for 3 months. You’ll need to use your judgement when investigating cases of ambiguous fraud and when you’re investigating the veracity of the model itself. We have to build robust models that are capable of updating their beliefs when they encounter new methods of fraud: our clients expect us to be one step ahead of fraud, not behind. You will be given the equipment, space and guidance you need to build world class fraud detection models. The work is not all green field research. The everyday work is about making safe incremental progress towards better models for our clients. The ideal candidate is willing to get involved in both aspects of the job – and understand why both are important. Key Responsibilities Responsibilities - Build out our model evaluation and training infrastructure. - Develop and deploy new models to detect fraud whilst maintaining SLAs - Write new features in our production infrastructure - Research new techniques to disrupt fraudulent behaviour - Investigate model performance issues (using your experience of debugging models). - Mentor junior members of the team Skills, Knowledge and Expertise Requirements - Significant experience building and deploying ML models using the Python data stack (numpy, pandas, sklearn). - Understand software engineering best practices (version control, unit tests, code reviews, CI/CD) and how they apply to machine learning engineering. - Strong analytical skills. - Being a strong collaborator with colleagues outside of your immediate team, for example with client support teams or engineering. - Being skilled at communicating complex technical ideas to a range of audiences. - The ability to prioritise and to manage your workload. - Being comfortable working with a hybrid team Nice to haves - Experience with Docker, Kubernetes and ML production infrastructure. - Tensorflow and deep learning experience. - Experience using dbt. - Experience with Go, C++, Java or another systems language. Benefits Benefits - Flexible Working Hours & Remote-First Environment — Work when and where you’re most productive, with flexibility and support. - Comprehensive BUPA Health Insurance — Stay covered with top-tier medical care for your peace of mind. - £1,000 Annual Wellness and Learning Budget — Prioritise your health, well-being and learning needs with funds for fitness, mental health, and more. - Monthly Wellbeing and Learning Day — Take every last Friday of the month off to recharge or learn something new, up to you. - 25 Days Holiday + Bank Holidays + 1 Extra Cultural Day — Enjoy generous time off to rest, travel, or celebrate what matters to you. - Mental Health Support via Spill — Access professional mental health services when you need them. - Aviva Pension Scheme — Plan for the future with our pension program. - Ravelin Gives Back — Join monthly charitable donations and volunteer opportunities to make a positive impact. - Fortnightly Randomised Team Lunches — Connect with teammates from across the company over in person or remote lunches every other week on us! - Cycle-to-Work Scheme — Save on commuting costs while staying active. - BorrowMyDoggy Access — Love dogs? Spend time with a furry friend through this unique perk. - Weekly Board Game Nights & Social Budget — Unwind with weekly board games or plan your own socials, supported by a company budget *Job offers may be withdrawn if candidates do not meet our pre-employment checks: unspent criminal convictions, employment verification, and right to work.*

• Execute assigned tasks to assist in the development and maintenance of analytical models, dashboards, and reporting outputs. • Analyze datasets using established statistical techniques and basic machine learning methods to support defined analytical objectives. • Apply foundational modeling approaches, including string‑matching and reconciliation techniques, to structured analysis tasks as directed. • Prepare intermediate analytical outputs (tables, summaries, visualizations) for review and iteration. • Execute data cleaning and transformation in Python or R, following established ETL and data processing workflows. • Draft clear summaries of findings and document data sources, assumptions, and methodologies in accordance with team standards. • Prepare charts, tables and dashboards visualizations to support stakeholder understanding and decision-making. • Support collaboration with internal teams and project stakeholders by gathering requirements and clarifying data needs. • Participate in code reviews, documentation reviews and team knowledge-sharing activities. • Assist with maintaining organized project files, analysis artifacts, and reference documentation.

• Serve as a subject matter expert in clinical data, including CCD data, claims, pharmacy, lab results, and clinical documentation. • Design and maintain clinical data models, taxonomies, and classification frameworks that enable consistent interpretation and use of clinical data across the organization. • Build the clinical data feature store, establishing standards, documentation, and best practices that accelerate adoption of clinical data for downstream analytics, reporting, and AI/ML use cases. • Develop analytics by building well-documented, validated, and reusable data assets (tables, views, features) that empower analysts and data scientists to work independently with clinical data. • Create and maintain comprehensive data documentation, including data dictionaries, lineage, business logic, known limitations, and appropriate use guidelines for clinical datasets. • Build queries, dashboards, and data visualizations to effectively communicate data quality metrics, data availability, and clinical insights to technical and non-technical stakeholders. • Partner with clinical, operational, and business stakeholders to understand their data needs, translate requirements into data solutions, and ensure clinical data assets meet their analytical objectives. • Maintain data quality frameworks for clinical data, including validation rules, anomaly detection, and monitoring processes to ensure data integrity and reliability. • Translate clinical concepts into analytical frameworks, ensuring that business partners understand the capabilities and limitations of available clinical data.

• Work with R&D leaders to set the vision for how product data science drives growth, especially in our acquisition and activation funnels. This includes how we use experimentation, causal inference, and behavioral analysis to identify and prioritize the most impactful opportunities. • Partner with Product, Design, and other R&D teams to refine and align on our metric tree, ensuring we are focused on the right measures of success and can clearly see the impact of our work. • Design and continuously refine how the product data science team operates within R&D: roles and responsibilities, collaboration models, team rituals, and how we partner with other data and R&D teams. • Manage and develop a team of data scientists supporting multiple areas within R&D. This includes 1:1s, performance reviews, feedback, and clear growth paths that build both technical and product/strategy skills. • Work with your team and cross-functional partners to design and maintain experimentation and measurement frameworks (e.g., clear hypotheses, guardrail metrics, success criteria) that can be reused across R&D and make it easier to run high-quality tests. • Collaborate with Data Analytics and Analytics Engineering to ensure that our metric tree and core growth KPIs are implemented consistently in our data models, documented clearly, and easily accessible across the company.