Machine Learning Engineer - Fraud Detection

We are backfilling a position after an internal move. This hire will help build out our ML platform: feature store, training pipelines, model registry and deployment. Remote position. Most of the team is in Brisbane, but nobody is required to come in.

What you'll be doing

• Maintain feature pipelines and a feature store such as Feast or Tecton
• Fine-tune open-weight models with LoRA when it beats prompting
• Productionize data science prototypes without rewriting everything
• Track experiments, artifacts and versions in MLflow or Weights & Biases
• Document model cards, data sources and known failure modes
• Orchestrate pipelines with Kubeflow, SageMaker Pipelines, Vertex AI or Airflow
• Build training pipelines in PyTorch or TensorFlow and run them on GPUs in AWS, GCP or Azure

Required qualifications

• Comfortable with SQL and large-scale data processing in Spark or Ray
• Familiarity with Docker, Kubernetes and a cloud ML platform (SageMaker, Vertex AI, Azure ML)
• Knowledge of LLM APIs, prompt design and evaluation methods
• Understanding of core ML concepts: overfitting, evaluation metrics, bias in training data
• Strong Python and solid engineering habits (testing, packaging, code review)
• Experience deploying models as services and monitoring them

Preferred qualifications

• Computer vision background (OpenCV, detection, segmentation)

Benefits

Rate: $180,000 - $210,000 per year

• Superannuation on top of salary
• Study leave
• Novated leasing

About Juneberry Commerce

Since 2013, the company has expanded from listings into payments, shipping and seller financing. More than 780 employees work on the product, from search ranking to fraud detection. Core hours are 10 to 3, and the rest of the day is flexible.

Shortlisting will begin immediately.

Start: Immediately.

Demo job created on 11jobs for testing and demonstrations. It is not an actual opening at Juneberry Commerce.