Key Notes
Python and an interest in predictive analytics are central to this London-based engineering position, explicitly described as hybrid. The role develops condition-monitoring methods for rail fleets and welcomes graduates or early-career applicants. An engineering degree is requested; railway experience is preferred, while industry experience is not essential.
What You'll Work On
- Develop condition-based maintenance algorithms from train signals and operational data, implementing prognostic logic through Python and related analytical tools.
- Analyse diagnostic and maintenance datasets, monitoring prognostic performance and identifying statistical trends that warrant further engineering investigation or action.
- Verify predictive algorithms using TCMS simulation, historical diagnostics and maintenance reports, comparing model behaviour with recorded field failures.
Why This Role Matters
- Rail fleet availability is affected by component failures; condition-monitoring algorithms connect diagnostic signals with maintenance interventions intended to reduce downtime and failure rates.
- Maintenance teams need credible predictive alerts, with simulation and historical failure comparisons testing whether algorithm outputs reflect the train conditions they are intended to identify.
What They Are Looking For
- Qualification: An engineering degree is requested, preferably in Electrical or Electronics Engineering.
- Technical: Strong Python coding skills and an interest in data analytics, machine learning or predictive technologies are essential.
- Technical: Relevant technical skills include SQL, SVN or Git, Power BI dashboards, statistical analysis and condition-based maintenance algorithms.
- Preferred: PySpark and railway experience are preferred; industry experience is beneficial but not required.