Job Description

We are looking for a data professional with strong expertise in Python, statistical modelling, forecasting, and building scalable data pipelines. The ideal candidate can work with large datasets, build predictive models, and create analytical systems that support decision-making and optimisation.

Key Responsibilities

Build and evaluate statistical & machine learning models
Develop forecasting models for performance and operational metrics.
Design clean, reliable data pipelines and feature engineering workflows.
Analyse large datasets to identify patterns, drivers, and insights.
Translate ambiguous analytical questions into structured modelling tasks.
Document processes and communicate findings clearly.

Core Skills (Required)

Strong Python skills (Pandas, NumPy, Scikit-Learn)
Experience with ML models (XGBoost / LightGBM / CatBoost)
Experience with regression, classification, and predictive modelling.
Time-series forecasting (Prophet, SARIMA, or similar).
Strong SQL: joins, window functions, analytical queries.
Ability to work with large datasets and build end-to-end pipelines.
Knowledge of data validation, evaluation metrics, and model monitoring.

Preferred (Nice but not required)

Experience integrating APIs, or working with any third-party data sources. •
Familiarity with cloud data warehouses (BigQuery / Redshift / Snowflake). •
Experience with dashboards (Power BI, Looker, Tableau).
Exposure to experimentation (A/B tests) or uplift modelling. •
Familiarity with feature stores or workflow schedulers (Airflow/Prefect)

Prior Experience Candidates should have experience in at least 2–3 of the following:

Built predictive or forecasting models in a previous role.
Worked with large-scale numeric datasets (product, sales, operational, etc.).
Developed ML pipelines from raw data to deployment.
Created statistical models for KPIs like conversions, transactions, orders, or performance metrics. •Implemented ETL/ELT data processes.

Background