Machine Learning Engineer

We are looking for an experienced and motivated Data Scientist – Time Series Forecasting & Microsoft Fabric to join our machine learning and data science team in London.

The successful candidate will help build, validate, deploy, and maintain reliable forecasting models using ARIMA, exponential smoothing, XGBoost, and modern Microsoft data platforms. This role is ideal for someone who enjoys translating real-world financial and insurance data into production-ready forecasts.

Responsibilities

• Design, build, and validate time-series forecasting models using ARIMA, exponential smoothing, and similar statistical methods.
• Develop and tune machine learning models using XGBoost and other gradient-boosting techniques.
• Use Microsoft Fabric data pipelines to ingest, clean, transform, and prepare structured and time-indexed data.
• Evaluate model performance using MAPE, backtesting, RMSE, MAE, and other relevant metrics.
• Perform feature engineering, model selection, validation, and iterative model improvement.
• Deploy and monitor models in production, ensuring forecasts refresh reliably through Fabric pipelines.
• Partner with machine learning, data engineering, and business teams to translate forecasting requirements into appropriate modelling approaches.
• Explain modelling choices, forecast uncertainty, assumptions, and limitations to non-technical stakeholders.
• Document modelling assumptions, validation results, model performance, and governance evidence.
• Support the use of model outputs in business-oriented applications and user interfaces.
• Recommend improvements to forecasting methods as data structures and business needs evolve.

Required Skills & Experience

• Bachelor’s or Master’s degree in Data Science, Statistics, Mathematics, Computer Science, or a related quantitative discipline.
• 4+ years of experience in data science, quantitative analytics, applied statistics, or machine learning.
• Hands-on experience building and tuning ARIMA or similar time-series models.
• Experience building and tuning XGBoost or comparable gradient-boosting models.
• Working knowledge of Microsoft Fabric.
• Strong Python skills, including Pandas, Statsmodels, Scikit-learn, and XGBoost.
• Experience with PySpark and solid SQL skills.
• Strong understanding of stationarity, seasonality, autocorrelation, time-series cross-validation, and bias-variance trade-offs.
• Experience evaluating and monitoring machine learning models in production.
• Strong communication skills and the ability to explain technical results to non-technical stakeholders.

Preferred Skills

• Experience with MLOps practices, including model versioning, ML CI/CD, model monitoring, and drift detection.
• Experience with Azure Machine Learning or other Microsoft cloud services.
• Exposure to insurance, actuarial, financial, or macroeconomic forecasting.
• Experience working in a regulated industry or supporting model governance and audit requirements.