Rail PM Engineer — Data-Driven Reliability

Hitachi Automotive Systems Americas, Inc.; Greater London; Hybrid; GBP 65,000 - 90,000; Full time

Benefits offered by this job

Competitive salary

Annual bonus

25 days holiday

Pension scheme

Private medical insurance

Group Life Insurance

Employee Assistance Programme

Job summary

Hitachi Rail UK Limited in London seeks a skilled Predictive Maintenance Engineer to join our hybrid team. You will develop tools to improve maintenance workflows and reliability using CBM/RCM, data science, and Python-based prognostics.

Strong rail or manufacturing experience and data analysis skills are essential. You will collaborate with the maintenance organisation to reduce downtime, validate prognostic models, and integrate diagnostics with TCMS interfaces.

Qualifications

• Engineering degree required or equivalent.
• Experience in railway domain or similar industry preferred.
• Strong coding skills in Python and SQL with exposure to PySpark.

Responsibilities

• Review and design main train subsystems focusing on maintainability, availability, reliability and CBM rule application.
• Develop prognostic algorithms, based on logic, signals and operational data.
• Implement prognostic algorithms using Python, PySpark and other technologies.
• Analyse diagnostics and maintenance data to identify trends and improve reliability.
• Study vehicle FMECA/FMEA and maintenance plans; support RCM design activities.

Skills

Python

SQL

PySpark

PowerBI

Data Science

RCM

CBM

Machine Learning

Big Data

UML

Education

Electrical/Electronics Engineering degree

Tools

Python

SQL

PySpark

Git

SVN

PowerBI

Job description

Hitachi Rail UK Limited in London seeks a skilled Predictive Maintenance Engineer to join our hybrid team. You will develop tools to improve maintenance workflows and reliability using CBM/RCM, data science, and Python-based prognostics.

Strong rail or manufacturing experience and data analysis skills are essential. You will collaborate with the maintenance organisation to reduce downtime, validate prognostic models, and integrate diagnostics with TCMS interfaces.