Full Stack Machine Learning Engineer

Reports To:
VP of R&D

Department:
R&D

Location:
Australia, Brisbane Preferred (Hybrid)

Employment Type:
Full time, permanent

About Dingo Software

Dingo Software is the global leader in predictive maintenance software for the mining industry, serving some of the world's largest mining companies. We drive efficiency, longevity, and reliability for machines that matter. With over 30 years of asset health data, we're scaling rapidly under The Riverside Company's ownership to capture significant market opportunities.

Following recent investment, Dingo is executing an ambitious growth strategy — embedding
AI and ML at the core of our products
to deliver smarter, faster, and more accurate insights for asset-intensive industries.

The Opportunity

As a Machine Learning Engineer at Dingo, you will design, build, and deploy production-grade ML models that power our predictive maintenance and integration platforms. You'll work on
one of the world's richest datasets of industrial machine health
— over three decades of curated asset health records combined with live data streams from sensors, inspection forms, operational logs, imaging, and mobile fleet telemetry systems.

This dataset provides a rare opportunity to build ML models that don't just run in lab conditions, but
make an immediate impact in the field
— improving equipment reliability, reducing downtime, and optimising asset performance for some of the world's largest mining operations.

You'll prototype and optimise models, design AI agents to automate monitoring and decision support, and deploy solutions via modern MLOps/LLMOps pipelines. You'll also collaborate with reliability engineers, data engineers, and product teams to integrate ML into customer-facing applications, driving measurable results in mining and other heavy industries.

Key Responsibilities

• Conduct exploratory data analysis and develop ML models for predictive maintenance, anomaly detection, time-series forecasting, and multimodal tasks.
• Develop and deploy requisite data cleaning, labelling, and preparation pipelines.
• Prototype, optimise, and validate models for Remaining Useful Life (RUL) estimation and condition-based maintenance.
• Design, build, and refine AI agents to automate equipment monitoring and decision support with human-in-the-loop validation.
• Deploy ML solutions into production using CI/CD-enabled MLOps/LLMOps pipelines, ensuring scalability, reliability, and monitoring.
• Build and maintain data pipelines for multimodal data (sensor, text, image, inspection forms, fleet telemetry), including edge deployments for low-connectivity mining environments.
• Collaborate with domain experts to ensure ML models are interpretable, explainable, and trusted by end-users.
• Explore and evaluate new techniques (graph neural networks, multimodal transformers, LLMs) for industrial AI use cases.

Required Skills & Experience

• Bachelor's or Master's degree in Computer Science, Data Science, Engineering, or a related field.
• 3+ years of ML engineering experience, with at least 1 year in industrial applications (IoT, predictive analytics, mobile fleet telemetry, or mining).
• Proven track record of deploying ML models into production, including time-series forecasting, anomaly detection, and classification.
• Strong proficiency in
  Python
  for end-to-end ML development.
• Expertise in ML frameworks (TensorFlow, PyTorch) and libraries (scikit-learn, Hugging Face).
• Experience with
  MLOps tools
  (MLflow, Kubeflow, SageMaker, or equivalent) for model versioning, monitoring, and retraining.
• Familiarity with
  agentic AI concepts
  (multi-agent systems, human-in-the-loop implementations).
• Understanding of data pipelines and ETL for multimodal datasets (sensors, images, text, fleet telemetry).
• Large-scale data preparation and pipeline development
• Cloud deployment experience (AWS, Azure, or GCP) with containerisation (Docker, Kubernetes).
• Knowledge of interpretable ML techniques (e.g., SHAP, LIME) to build trust in model predictions.

Nice to Have

• Experience with
  predictive maintenance or condition monitoring
  (e.g., vibration analysis, oil analysis, fleet telemetry).
• Familiarity with
  mobile mining equipment and fleet management systems
  .
• Experience with
  computer vision
  (thermal imaging, defect detection, corrosion monitoring).
• Exposure to
  graph neural networks
  or multimodal AI for industrial systems.
• Contributions to open-source ML projects or publications in industrial AI.

Success Measures

• Delivery of robust ML models that achieve targeted accuracy, reliability, and business impact.
• Successful deployment of ML solutions that operate reliably at scale in production and edge environments.
• Demonstrated improvement in predictive maintenance outcomes (e.g., reduced downtime, improved equipment reliability).
• Strong collaboration with engineers, product managers, and customer stakeholders.
• Ongoing adoption of new AI/ML innovations that differentiate Dingo's product suite.

Compensation & Benefits

• Competitive base salary
• Performance bonus
• Professional development opportunities
• Flexible hybrid working arrangements

Diversity & Inclusion

At Dingo, we believe diversity drives innovation and inclusion fuels success. We welcome applicants from all backgrounds and encourage those who don't meet every qualification to apply — you might be the right candidate for us.

How to Apply

Interested candidates are invited to submit a detailed CV/resume and cover letter outlining their relevant experience and qualifications. All applications will be treated in strict confidence, and only shortlisted candidates will be contacted.