Data Scientist: Python, DevOps & Geospatial (6-Month)

HiTech Personnel; Canberra; On-site; AUD 83,000 - 165,000; Full time

Job summary

HiTech Personnel is seeking a Data Scientist to design and implement scalable data science workflows for a federal program across multiple Australian locations. The role focuses on Python development, geospatial processing, and cloud/DevOps practices in a fast-paced, agile setting.

The successful candidate will contribute to geospatial data pipelines, collaborate with science stakeholders, and deliver high-quality, well-documented code for robust, reusable solutions in both supercomputing and

Qualifications

• Knowledge, experience, and/or qualifications in coding and software development (ideally Python, Fortran).
• Experience in image processing and classification using remote sensing algorithms and/or ML techniques with optical and/or SAR data.
• Experience with DevOps practices (CI/CD and infracode) and cloud computing (AWS preferred).

Responsibilities

• Develop projects to implement solutions within an agile work environment.
• Integrate geospatial information systems, data pipelines and processing techniques for supercomputing and cloud environments.
• Develop and maintainable and well-documented Python code, ensuring high quality across the team.
• Communicate technical issues to a wide audience, including a technical lead, program manager, other project members and science stakeholders.

Skills

Python

Fortran

Geospatial analysis

Machine Learning

CI/CD

AWS

Cloud computing

Remote sensing

Tools

xarray

pandas

NumPy

Job description

HiTech Personnel is seeking a Data Scientist to design and implement scalable data science workflows for a federal program across multiple Australian locations. The role focuses on Python development, geospatial processing, and cloud/DevOps practices in a fast-paced, agile setting.

The successful candidate will contribute to geospatial data pipelines, collaborate with science stakeholders, and deliver high-quality, well-documented code for robust, reusable solutions in both supercomputing and