Data Scientist
Core
Refactor and optimize a large-scale microsimulation model for Australia's labour market and skills system, transitioning it from R to a stable, scalable production environment in Azure Databricks.
Role type
Senior Data Scientist / Data Engineer (Microsimulation)
Builds
A stable, scalable production microsimulation model for labour market analysis
Domain
Federal Government, Labour Market, Statistical Modelling
Deliverable
production ML models
Required skills
Advanced R development, Statistical/simulation modelling, Azure Databricks, Apache Spark, Python, Refactoring, Performance optimisation, Unit testing, Version control, Scenario testing, Model validation
Preferred skills
Azure Data Factory, Delta Lake, Unity Catalogue, Labour market datasets, ABS data
Technologies
R, Python, Azure Databricks, Spark, Azure Data Factory, Delta Lake, Unity Catalogue
Responsibilities
Review and refactor complex R codebases, Improve model and compute performance, Develop repeatable scenario testing, Support Python and Spark-based data pipelines, Strengthen engineering practices (testing, version control, monitoring, logging, documentation), Ensure model accuracy while improving operational efficiency
Seniority
Senior, hands-on IC
