Staff Data Scientist (Fraud & Risk)
Tide
India, HyderabadPosted 26 days ago
Skill Required
One PlatformData ScientistMachine LearningDeep LearningETLObservabilityCD pipelinesLangChainEngineeringR ProgrammingData StructuresbuildingXGBoostPyTorchPythonHadoopdesignSparkCI/CDCloudGenerative AISQLAWSGCPCICDAI
Key highlights
- Competitive salary and share options
- 10+ years of experience required
- Private family health insurance
- Work from abroad for up to 90 days annually
- Flexible workplace model (remote and in-person)
- Great Place to Work certified
Role overview
As Staff Data Scientist for the Fraud & Risk area at Tide, you will work closely with cross-functional teams to deliver Company, Business, and Product OKRs. You will lead the development of advanced classical Machine Learning models for global fraud detection, risk assessment, and anomaly detection, while also implementing and scaling production-ready GenAI and Agentic AI workflows. As a Subject Matter Expert (SME), you will set technical standards, address highly imbalanced data use cases, and ensure models adapt to evolving fraud patterns and data drift in production pipelines.
Responsibilities
- Design and develop advanced predictive ML models tailored for global fraud detection, risk assessment, and anomaly detection.
- Design and develop production-grade GenAI and Agentic AI solutions (leveraging frameworks like LangGraph on AWS or GCP) to automate alert handling and accelerate fraud investigations.
- Tackle highly imbalanced datasets using advanced techniques, ensuring models optimize for real business impact (minimizing false positives while catching evolving fraud).
- Proactively identify, measure, and resolve data drift and concept drift in production pipelines to maintain continuous model performance.
- Present compelling insights and demonstrate strong storytelling skills to translate complex model outputs for non-technical stakeholders.
- Act as the definitive technical IC and SME for the team—setting technical standards and reviewing architectures to push the boundaries of what 'best' looks like.
- Collaborate with ML engineers to deploy models, establish CI/CD pipelines, and implement robust model tracking and observability.
- Partner with Data Engineering to optimize feature engineering and feature stores for real-time and batch fraud decisioning.
- Work with Product and Business teams to translate complex fraud typologies and business requirements into rigorous mathematical formulations and data science problems.
- Build and track metrics for the performance of models and their direct impact on the business bottom line, feeding this back to Product and Business Teams.
- Deal with ambiguity and propose innovative solutions without getting blocked.
Requirements
- 10+ years of experience in Data Science or Machine Learning, with a substantial portion dedicated to fighting fraud or risk mitigation in a fast-paced environment.
- Highly comfortable acting as a dedicated, fully hands-on technical Individual Contributor (IC) and leading by example.
- Deep, theoretical, and practical understanding of classical machine learning algorithms (e.g., XGBoost, LightGBM, Random Forests, SVMs, Ensemble methods) and statistical modeling.
- Strong experience building adversarial models for fraud detection and working with synthetic data generation to bolster model robustness.
- Hands-on experience taking GenAI and multi-agent systems to production (using tools like LangGraph, AWS Bedrock, or GCP ecosystem) that have delivered real, measurable ROI.
- Extensive hands-on experience handling highly imbalanced datasets, utilizing appropriate sampling methods, cost-sensitive learning, and relevant evaluation metrics (Precision-Recall AUC, F1-score, custom loss functions).
- Strong hands-on experience detecting and addressing data drift, concept drift, and model degradation in production systems.
- Good technical knowledge in SQL, strong in Python programming (including exposure to PyTorch and Hugging Face), and a good understanding of performance optimization in the end-to-end data pipeline including ML/DS inferencing.
- High-level understanding of big-data technologies such as Spark, Hadoop, etc.
- Strong knowledge of Cloud (AWS or GCP).
- Self-starter who can work comfortably in a fast-moving company where priorities can change and processes may need to be created from scratch with minimal guidance.
Nice to have
- Demonstrated technical inclination, such as submitting or publishing research papers at technical conferences, holding patents, or making significant open-source contributions.
Benefits
- Competitive salary and share options
- Generous annual leave on top of bank holidays
- Paid maternity, paternity, and adoption leave
- Extended unpaid and paid sabbatical leave options after completing milestone years with Tide
- Private family health insurance with additional OPD coverage and top-up options
- Comprehensive accidental and life insurance protection
- Access to therapy sessions, courses, meditations, and workshops for mental wellbeing
- Paid days annually for volunteering or personal growth
- Annual budget for books, courses, coaching, and more
- Work from abroad for up to 90 days annually (WOO - Work Outside the Office)
- Contribution towards setting up your home office
- Keep your old laptop and get a new one when it’s time for a replacement
- Office perks with snacks, coffee, tea, and lunch (location dependent)
Additional details
- This role is an Individual Contributor (IC) position.
- Tide is available for UK, Indian, German and French SMEs
- Over 2 million members: 900,000 UK and 1,100,000 in India and growing rapidly
- Over $300 million raised in funding
- Over 2,800 Tideans globally
- Recognised with Great Place to Work certification three years in a row, and among India’s Top 50 Best Workplaces in Banking, Financial Services, and Insurance in 2026
- Offices in Central London, Sofia (Bulgaria), Serbia, Romania, Lithuania, Hyderabad, Gurugram, New Delhi, Berlin, Paris, and Luxembourg
- Tide champions a flexible workplace model supporting both in-person and remote work, with offices designed as hubs for innovation and team-building.
- Tide is committed to diversity, equity, and inclusion, fostering a transparent and inclusive environment where everyone’s voice is heard.
- Tide does not charge fees at any stage of the recruitment process; all official job opportunities are listed on the Careers Page, and communication comes only from @tide.co email addresses.
- Tide leverages AI to enhance the hiring experience, as outlined in the AI Policy.
- Personal data will be processed in accordance with Tide's Recruitment Privacy Notice.
- Tech stack includes Databricks on AWS/GCP, Python, Snowflake/BigQuery, Tecton/Databricks (feature store), and Fiddler (model observability platform).