Data Scientist | Machine Learning & Financial Engineering | Permanent | London 3 days a week | up to £100k per annum

Experience Level: 2+ Years
Technical Stack: Python, AWS, Machine Learning

The Opportunity

We are seeking a proactive and analytically-driven Data Scientist to revolutionise the way our client process and validate complex financial data.

In this role, you will lead the transition from a manual, prototype-based cleaning process to a fully automated, scalable Machine Learning pipeline. You will be responsible for identifying outliers within large-scale datasets, ensuring the accuracy of consensus pricing for financial derivatives, and building a system that learns and improves through a continuous human-in-the-loop feedback mechanism.

Key Responsibilities

• Model Design & Development: Design, build, train, and validate sophisticated ML models (including Random Forests and Boosted models) to automatically flag "bad" valuations across multiple dimensions.
• Pipeline Automation (AWS): Build robust, production-ready data pipelines within the AWS ecosystem (S3, Lambda, etc.) to process high daily volumes of valuation data within tight windows.
• Explain ability & Confidence: Develop methods to measure model confidence and provide clear reasoning for valuation decisions. You will ensure the system flags borderline cases for expert review to maintain high integrity.
• Continuous Learning: Implement feedback loops where human corrections are automatically integrated into training data, allowing the model to evolve and improve accuracy over time.
• Collaborative Innovation: Generate and test hypotheses to drive incremental progress, working closely with both technical teams and business stakeholders.