Senior Data Scientist

ABOUT TIDE At Tide we help SMEs save time (and money) in the running of their businesses by not only offering business accounts and related banking services, but also a comprehensive set of highly usable and connected administrative solutions from invoicing to accounting. Tide is transforming the small business banking market with over 1.8 million members globally across the UK, India, Germany and France. Using advanced technology, all solutions are designed with SMEs in mind. With quick onboarding, low fees and innovative features, we thrive on making data-driven decisions to serve our mission: to help SMEs save both time (and money) so they can get back to doing what they love. Tide facts: Tide is available for UK, Indian, German and French SMEs Over 1.8 million members: 800,000 UK and 1,000,000 in India and growing rapidly Over $300 million raised in funding Over 2,500 Tideans globally - we’re diversity champions! We have offices in Central London, with a member support and technology centre in Sofia, Bulgaria, technology centres in Serbia, Romania, Lithuania and Hyderabad and offices in Gurugram and New Delhi, and in Berlin, Paris and Luxembourg. ABOUT THE ROLE You are a seasoned Data Scientist, passionate about building robust, real-time machine learning solutions to combat financial crime. Working within the Risk Fraud Team, you will leverage advanced statistical modeling and machine learning to detect, prevent, and adapt to evolving fraud threats. You thrive on solving complex problems with highly imbalanced data and delivering tangible risk reduction impact in a fast-paced environment. You strongly believe in agile principles and use them to deliver value incrementally. You are eager to learn about new methodologies and practices and apply them directly in your work. As a Senior Data Scientist you’ll be: Model Development Risk Mitigation: Design, develop, and implement advanced ML/Statistical models to predict and prevent various fraud typologies. Focus on driving impact by optimising costs and reducing risk using ML/Stats models. Specialised Data Handling: Employ advanced techniques to manage and model highly imbalanced, large datasets characteristic of the fraud domain. Adaptive Systems: Build and maintain models that can quickly adapt to new and evolving fraud typologies and emerging threats. Real-Time MLOps: Develop, optimise, and deploy ML models for real-time/low-latency inference in production settings. Data Feature Engineering: Utilize, enrich, and contribute to the feature store ecosystem, ensuring high-quality, scalable features for risk models. Performance Monitoring: Implement and maintain robust drift monitoring and model performance tracking to ensure deployed models remain effective and stable. Collaboration: Work closely with ML Engineers to productionize models leveraging AWS/GCP tech stack, and collaborate with Business and Product teams to understand requirements and solutionise data products. Exploration : Identify creative solutions in order to build relevant training data sets and explore the value of new data structures like knowledge graphs for relational fraud detection. WHAT ARE WE LOOKING FOR You have 4+ years of experience in Software Development or Machine Learning, with a strong emphasis on practical model development and deployment. You are Strong in Python and have expert knowledge with Machine Learning tools/libraries (e.g., scikit-learn, statmodels, TensorFlow, Keras, or PyTorch). You have experience with big-data technologies such as Spark, SparkML, Hadoop etc. and have handled large data in a distributed processing environment. AWS, GCP, or Azure (anyone) cloud knowledge is preferred. You are proficient in ML training, optimising, feature selection and engineering, hyperparameter tuning and have knowledge about trade-offs in using different algorithms. You have demonstrated experience in developing and deploying a variety of ML-algorithms (e.g., logi ... (truncated, view full listing at source)