About BHP
At BHP we support our people to grow, learn, develop their skills and reach their potential. With a global portfolio of operations, we offer a diverse and inclusive environment with extraordinary career opportunities. Our strategy is to focus on creating a safe work environment where our employees feel strongly connected to our values and objectives, and where the capability of our people is key to our success.
Come and be a part of this success.
About the Role
As the Specialist Asset Health Development, you will be responsible for the development and maintenance of predictive analytics models for Asset Health diagnosis and prognosis of BHP equipment. This role is Python-first and focused on time-series analytics (e.g., trending, deviations from trend, drift and early warning detection, baseline/expected behaviour bands), using enterprise historian data (e.g., AVEVA PI) and curated datasets in Snowflake to deploy repeatable, scalable analytics patterns across sites and asset classes.
Reporting to the Project Manager Predictive Maintenance, your key responsibilities will include:
1) Develop and maintain time-series Asset Health analytics
- Develop Python analytics scripts to identify degradation, drift, abnormal behaviour, and deviations from expected operating trends using equipment time-series and condition monitoring data.
- Perform time-series preparation and analytical feature engineering (e.g., resampling, smoothing/filters, rolling statistics, baseline modelling, rates-of-change, event-windowing)
- Apply statistical and/or machine learning techniques where appropriate, with a preference for interpretable and operationally trusted analytics that translate clearly to maintenance action.
- Produce clear documentation of logic, assumptions, thresholds, and limitations to support operational adoption and repeatability.
2) Scale analytics patterns across equipment types and sites
- Support delivery of the Asset Health program of work to scale and deploy analytics patterns to similar equipment types, leveraging consistent failure modes and monitorable symptoms with guidance from reliability engineers.
- Standardise reusable analytics patterns (templates, parameterisation, QA checks) that enable efficient replication across fleets and operating contexts.