Description:
Application closing date: Monday, 28 July 2025 • 11:59pm, Canberra time
Estimated start date: Tuesday, 26 August 2025
Location of work: ACT
Working arrangements: Applicants will be expected to work at the AEC's.Hybrid working arrangements (i.e. a combination of onsite attendance at an AEC office and remote working) will be considered at the discretion of the Hiring Manager with a typical 3 days in the office and 2 days working from home.
Length of contract: Until 30 June 2026
Contract extensions: 1x 12 months
Security clearance: Must be able to obtain Negative Vetting Level 1
Rates: $90 - $120 per hour (inc. super)
Within the Australian Electoral Commission (AEC) the Indigo Program is a large-scale transformation program to modernise business capabilities and replace core election ICT systems with a citizen-centric, agile technology platform. The Program will transform the AEC’s delivery of electoral services and ensure ongoing integrity of the electoral system. Tranche 2 comprises a variety of work packages with a focus on business process re-engineering, data management, legislative compliance and replacing aging systems.
The Python Developer will be responsible for designing, developing, and deploying end-to-end data science solutions within the Microsoft Azure and Databricks environment. This role will involve working with large datasets stored in Azure Data Lake Storage (ADLS) Gen2 and Databricks, building and training machine learning models using Python and relevant libraries, and implementing automated pipelines for model deployment and operationalization. The ideal candidate will be a self-starter with a strong understanding of the data science lifecycle, capable of translating business problems into technical solutions and effectively collaborating with cross-functional teams.
The Python Developer will be responsible for, but not limited, to:
- Develop, test, and maintain Python-based applications, scripts, and tools.
- Develop and implement robust Python-based solutions to efficiently read, process, and transform large datasets from Azure Data Lake Storage (ADLS) Gen2, Synapse and Databricks environments, ensuring data quality and readiness for model development.
- Design, implement, and train machine learning models using relevant Python libraries (e.g., scikit-learn, TensorFlow, PyTorch, MLflow within Databricks) to address specific business problems, iterating on model architecture and hyperparameters to achieve optimal performance.
- Develop and implement automated pipelines and deployment strategies (e.g., using Databricks Model Serving, Azure Machine Learning, containerisation) to seamlessly integrate trained models into production environments, ensuring scalability and reliability.
- Design and build automated workflows using Python and Azure services (e.g., Azure Data Factory, Databricks Workflows) to streamline data ingestion, model training, evaluation, and deployment processes, ensuring efficiency and repeatability.
- Implement monitoring solutions to track model performance and data drift in production, perform regular model evaluation, and develop strategies for model retraining and maintenance to ensure continued accuracy and relevance.
- Effectively collaborate with data engineers, business analysts, and other stakeholders to understand business requirements, communicate technical findings, and contribute to the overall data science strategy.
- Adhere to coding best practices, including version control, code documentation, and testing, to ensure maintainable, scalable, and high-quality Python code.
Essential Criteria
- Proficiency in Python and its frameworks (e.g., Django, Flask, FastAPI).
- Solid proficiency in Python programming and relevant data science libraries (e.g., Pandas, NumPy, scikit-learn).
- Demonstrable experience building, training, and evaluating machine learning models using frameworks such as scikit-learn, TensorFlow, PyTorch, or similar.
- Strong problem-solving and analytical skills with the ability to translate business requirements into technical solutions.
- Experience with RESTful APIs and microservices architecture.
- Ability to handle and respect the sensitivities of datasets and the use of Personally Identifiable Information (PII)
Desirable Criteria
- Familiarity with DevOps practices and CI/CD pipelines.
- Experience with Databricks, including using Spark for data processing and MLflow for model management.
- Experience with at least one model deployment framework or service (e.g., Databricks Model Serving, Azure Machine Learning.
- Bachelor's or Master's degree in a relevant field (e.g., Computer Science, Data Science, Statistics, Engineering).
HOW TO APPLY
Please provide an updated CV (a maximum of 3 pages) to reflect your suitability to the role based on the job description. You will also need to complete a response to the Essential and Desirable criteria above in a summary no more than 5000 characters in total.