Azure Machine Learning Expert

Role :

We are seeking an experienced Azure Machine Learning Specialist to lead the development and deployment of advanced predictive models that enhance the accuracy and reliability of student number forecasting. The role will involve building high-accuracy forecasting systems using Azure ML, integrating multiple data sources, and deploying models through scalable and automated pipelines that drive strategic planning decisions. The consultant will work closely with Data & Analytics and Planning teams to design, train, and validate models using Azure ML Studio, Python, and Data bricks while ensuring adherence to the institution’s data governance and security standards. The ultimate objective is to achieve 99% accuracy in student number forecasts at least three months prior to each intake, empowering effective resource allocation and data-driven planning.

Key Responsibilities :

Conduct detailed audits of CRM, application, and enrolment datasets in Azure to assess data quality, completeness, and modelling suitability

Design, develop, and implement machine learning models to forecast student numbers across multiple intakes, covering variations by course, mode, location, and student type.

Advanced statistical and machine learning methods (ARIMA, Prophet, Gradient Boosting, Random Forest, LSTM) to maximise forecast accuracy, interpretability, and reliability Validate, test, and refine models using recognised performance metrics such as RMSE, MAPE, and R-squared to achieve the required accuracy levels.

Integrate forecasting models into existing Azure-based data pipelines, leveraging Data Factory, Synapse, and Data Lake services.

Automate model training and deployment cycles following MLOps and CI / CD best practices (using MLflow, DVC, GitHub Actions, and Azure DevOps).

Embed model outputs within Power BI dashboards and other visualization tools for business and academic users, Develop scalable, maintainable solutions to ensure forecasts can be easily retrained and updated

Collaborate with university stakeholders through virtual workshops, progress meetings, and hands-on knowledge transfer sessions.

Requirements :

Minimum 7–10 years in data science, ML engineering, or predictive analytics, including at least 3 years of hands-on experience with Azure ML and related Azure data services (Data Factory, Synapse, Data Lake).

Proven ability to independently design, build, deploy, and validate complex predictive models to a high standard of accuracy.

Experience integrating predictive models into Power BI dashboards or similar tools

Demonstrable success in applying time-series forecasting and ML techniques to real-world business or operational planning problems

Exposure to the education sector, particularly in student recruitment, admissions, or enrolment forecasting, is a strong advantage

Experience mentoring or training others in ML model maintenance and best practices

Advanced programming proficiency in Python (Pandas, Scikit-learn, PyTorch / TensorFlow)

Expertise in time-series forecasting using Prophet, ARIMA, and LSTM frameworks

Strong knowledge of data reprocessing, feature engineering, model validation, and MLOps within Azure environments.

Excellent written and verbal communication skills with the ability to explain complex technical concepts to non technical stakeholders.