Senior Data Scientist - Machine Learning, Utilities

About the role

A growing data and AI business, expanding in Melbourne since early 2024, is building its local team. It works with utility providers, infrastructure, telecommunications and retail clients, using machine learning, advanced analytics and modern data platforms. The client is helping a major electricity distributor assess new connections and plan its network, from smart meter data platforms to production machine learning models, and is also integrating generative AI tools.

Key responsibilities

• Develop and deploy supervised and unsupervised machine learning models that support operational and investment decisions for utility providers
• Work across the full project lifecycle, from understanding business requirements and exploring data to engineering features, evaluating models and integrating predictions into business processes
• Work with stakeholders to define the problem, measure success and explain results, uncertainty and limitations
• Build reliable training and prediction pipelines with data engineers, write tested code and manage deployments via Git, CI/CD and Declarative Automation Bundles
• Monitor model performance, investigate errors and improve models as new data and requirements emerge
• Help colleagues build data science and machine learning skills through joint development, code reviews and training
• Apply generative AI where it improves access to data and model outputs in business workflows

Required profile

• Degree in a quantitative discipline (engineering, computer science, mathematics, statistics or physics) or equivalent experience
• Strong mathematical, statistical and machine learning foundations
• Existing Australian work rights strongly preferred due to the required start date
• Ability to work directly with stakeholders and collaborate with engineers

Required skills

• Python, pandas, scikit-learn, NumPy and SciPy
• Supervised and unsupervised machine learning, feature engineering and pipeline building
• MLflow or similar tools for experiment tracking and model registration
• Databricks and cloud services such as AWS or Azure
• PySpark for large datasets, Git, code review, automated testing and CI/CD
• Desirable: smart meter, time series, geospatial or network asset data; model monitoring, drift detection and retraining; Databricks Unity Catalog; generative AI tools such as Databricks Genie

What we offer

• Competitive salary and performance-based bonus scheme
• Annual leave and employer-paid superannuation
• Learning and development budget
• Hybrid working
• Access to Databricks and cloud infrastructure