Data Scientist

Role Overview

We are looking for an experienced Data Scientist/Data Engineer with strong expertise in predictive modelling, forecasting, SQL development, and data engineering. The ideal candidate will build forecasting models and develop reliable data pipelines using Databricks, SSIS, and SQL Server.

Responsibilities

• Develop and improve predictive models and forecasting solutions.
• Analyse historical data to identify trends, patterns, seasonality, and key influencing factors.
• Perform data preparation, feature engineering, model training, validation, and performance evaluation.
• Evaluate models using appropriate metrics such as MAE, RMSE, and MAPE.
• Build and maintain scalable data and ETL pipelines using Databricks and SSIS.
• Develop and optimize SQL queries, stored procedures, and database objects.
• Integrate data from multiple sources into SQL Server and Databricks.
• Deploy, monitor, and retrain forecasting models to maintain accuracy.
• Investigate data-quality issues, prediction errors, and model performance changes.
• Use Git for version control and collaborative development.
• Collaborate with engineering, analytics, and business teams to convert requirements into actionable forecasting solutions.
• Present model outputs and business insights through reports and dashboards.

Requirements

• Experience in predictive modelling and forecasting
• Strong knowledge of statistical analysis, machine learning, and time-series forecasting
• Strong programming experience with Python and/or PySpark
• Strong SQL development skills
• Hands-on experience with Databricks
• Expertise in SSIS
• Strong knowledge of SQL Server
• Experience with data preparation, feature engineering, and model evaluation
• Experience using Git for version control

Skills

• Python
• SQL
• Databricks
• PySpark
• SSIS