- Data Scientist (Simulation)
Application closing date: Monday, 08 August 2022 • 11:59pm, Canberra time (in Canberra)
Estimated start date: Monday, 22 August 2022
Location of work: ACT
Length of contract: 6 Months
Contract extensions: 2x 12 months
Security clearance: Must have Baseline
Rates: $120 - $150 per hour (inc. super)
The Department of Agriculture, Fisheries and Forestry (DAFF) has undertaken an initiative to improve its biosecurity risks under the recently established Digital Reform Division. DAFF aims to develop an Enterprise Pest Management system and integrate it with the department’s critical biosecurity information system.
We are looking for data scientists that can work across the Azure technology stack to deliver outcomes that improve risk management capabilities across the cargo pathway and support the movement of shipping containers of imported goods into Australia. We are looking for a data scientist with experience and skills in statistical simulation, probability theory and scientific computing, as well as experience or a desire to learn the Microsoft Azure platform. The focus will be on models developed in R.
Technologies you might work with:
- programming languages like Microsoft SQL, R and MATLAB Python, Jupyter Notebooks, Spark PyTorch , Keras , Tensorflow, SciKit Learn Microsoft Azure (Azure Cognitive Services, Azure Machine Learning, Databricks)
- ALM Azure DevOps tooling Data Preparation, cleansing, transformation and loading Model – Discovery, Plan, Build, Test and Operationalise Define and create data structures
What you will work on:
- Continuous development of our clients’ machine learning platform and products based on mainly Azure
- Identifying, creating and preparing data required for machine learning algorithms
- Deploying and maintaining machine learning solutions in production Using Agile/SCRUM methodology
- Depending on your experience you might work on custom machine learning solution architecture, design, definition and implementation
The ideal candidate will have:
- Strong mathematical skills to help collect, measure, organize and analyze data
- Technical proficiency regarding database design development, data models, techniques for data mining, and segmentation
- Advanced experience with building applications in one of the major languages, preferably R (alternatively Python)
- Experience with R scientific computing and parallelisation libraries
- Real life experience with statistical simulations and applied probability theory in various domains (e.g. biosecurity)
- Experience with Azure cloud technologies including Azure Databricks Real life experience in Image Recognition and Computer Vision (object detection, classification)
- Familiar with machine learning libraries l
- Proven experience in implementing Analytics in Microsoft Azure environment. Working R scientific computing and parallelisation libraries, statistical simulations and applied probability theory.
- Data science model architecture, design and implementation on Azure Databricks and Implementation.
- Programming skills to collect, analyze, and interpret large data sets to develop data-driven solutions for business challenges.
- Experience in leading the design and development activities using Agile product development environment and familiarity with Agile ceremonies.
- Real life experience in Image Recognition and Computer Vision (object detection, classification).
- Proven experience in implementing Machine Learning models (e.g Deep Learning), ML development frameworks like Tensorflow, Pytorch, scikit learn etc.