Hybrid Data Scientist — Time Series Forecasting

Synechron; Greater London; Hybrid; GBP 65,000 - 95,000; Full time

Job summary

Synechron seeks a mid-level Data Scientist to build and maintain forecasting models. You will work with time series methods (ARIMA, exponential smoothing) and gradient-boosted models (XGBoost), developing solutions in Microsoft Fabric for production deployment.

You will ingest, clean, and transform structured time-indexed data, evaluate model performance with metrics like MAPE and backtesting, and collaborate with the ML team to translate forecasting requirements for business stakeholders.

Qualifications

• 4+ years of experience in data science, quantitative analytics, or applied statistics.
• Hands-on experience building and tuning ARIMA and XGBoost models.
• Proficiency in Python (pandas, scikit-learn) and SQL; familiarity with PySpark is a plus.
• Experience with Microsoft Fabric or similar data platforms is desirable.
• Exposure to financial services or macroeconomic data is a plus.

Responsibilities

• Design, build, and validate time series forecasting models (ARIMA, exponential smoothing) and ML models (XGBoost).
• Ingest, clean, and transform structured, time-indexed data using data pipelines in Fabric.
• Evaluate model performance using statistics and ML metrics (MAPE, backtesting) and iterate on features.
• Deploy and monitor models in production within Fabric pipelines.
• Collaborate with ML teams and stakeholders to translate forecasting needs into modeling solutions.
• Document modelling assumptions, validation results, and governance artifacts.
• Stay updated on advances in time series forecasting and ML methods.
• Support the wider ML team in operationalizing model outputs for business use.

Skills

Time series forecasting

ARIMA

XGBoost

Python

PySpark

SQL

Education

Bachelor's or Master's in Data Science/Statistics/Mathematics/Computer Science

Tools

Microsoft Fabric

Job description

Synechron seeks a mid-level Data Scientist to build and maintain forecasting models. You will work with time series methods (ARIMA, exponential smoothing) and gradient-boosted models (XGBoost), developing solutions in Microsoft Fabric for production deployment.

You will ingest, clean, and transform structured time-indexed data, evaluate model performance with metrics like MAPE and backtesting, and collaborate with the ML team to translate forecasting requirements for business stakeholders.