Forward-Deployed Architect, Credit Analytics & ML Platforms

About the role

A regulated financial-services business operating in the UK and Ireland is looking for a hands-on Forward Deployed Engineering (FDE) Architect to help build a credit analytics platform. The platform combines lending and servicing data to support portfolio analysis, credit-risk modelling and better business decisions, covering probability of default, redemption and prepayment, expected credit loss and interactive analytics. The architect works directly with the client's business and technology teams, alongside a credit-domain and modelling lead, and owns the engineering architecture while contributing production code.

Key responsibilities

• Translate business problems into an architecture, delivery plan and acceptance criteria, and design the path from working models and dashboards to a production-ready ML platform.
• Build reproducible workflows for data preparation, feature engineering, training, validation, scoring and deployment, with clear versioning of code, data, models and calibration logic.
• Work with the modelling lead on how probability of default, prepayment, lifetime risk and loss estimates are calculated, tested and exposed to applications, keeping business definitions consistent across models, tables and dashboards.
• Strengthen the data foundation by tracing results to source, investigating data-quality issues, documenting assumptions and building automated checks.
• Improve the reliability of the Snowflake-backed analytics application, including deployment, testing, permissions and integration with model outputs.
• Put MLOps practices in place: repeatable releases, monitoring, failure handling, rollback and operational documentation.
• Design for privacy, access control, auditability and model governance, and work with domain experts on validation, stability and fairness checks.
• Lead technical discussions, review code, unblock engineers and keep the client informed; assess where natural-language or LLM-assisted analytics could add value.

Required profile

• Track record of designing and delivering production data or ML systems, with ownership beyond prototypes and architecture diagrams.
• Experience leading a small technical team while staying actively involved in implementation.
• Ability to work through incomplete documentation and inconsistent business definitions, and strong client-facing communication in English.

Required skills

• Strong hands-on Python and SQL.
• Practical MLOps experience: reproducible pipelines, versioning, testing, deployment and monitoring.
• Experience with cloud data platforms and modern warehouses; Snowflake experience is particularly relevant.
• Understanding of model evaluation, calibration, data leakage and the difference between model quality and system reliability.
• Useful additional experience: credit-risk analytics (PD, LGD, ECL, prepayment, stress testing), regulated financial-services delivery, Streamlit, Azure ML, configurable ML products, and evaluated natural-language or text-to-SQL workflows.