PHM Monitor Development Engineer
Job Description
We are seeking a highly skilled Contract Prognostics & Health Monitoring (PHM) Engineer to design, develop, and deploy offline health monitoring algorithms and prognostic models for our fleet of autonomous vehicles
In this role, you will focus strictly on the backend development and deployment of algorithms that analyze historical and batch telemetry data. Your work will directly enable our maintenance teams to predict component failures, estimate Remaining Useful Life (RUL), and optimize our preventative maintenance schedules
Responsibilities
Define technical requirements for new health monitors by identifying the problem, the required telemetry data, and the data to be used for validation.
Design and train data-driven and/or physics-based prognostic models to detect faults and estimate the Remaining Useful Life (RUL) of critical hardware components.
Develop offline diagnostic algorithms to detect anomalies, wear-and-tear patterns, and early fault indicators using batch telemetry, sensor logs, and historical maintenance data.
Clean, filter, and extract relevant features from large volumes of time-series sensor data (e.g., vibration, temperature, voltage, pressure).
Perform large-scale ETL and data manipulation using PySpark on Databricks clusters.
Engineer, package, and deploy developed models using production-grade pipelines.
Design and implement fleet result dashboards to visualize monitor output.
Develop a robust alerting strategy, secure stakeholder confirmation, and configure alert delivery.
Rigorously back-test prognostic models against historical failure data to ensure high accuracy, low false-positive rates, and reliability.
Provide clear technical documentation of model architectures, deployment procedures, and codebases to ensure a smooth handover at the end of the contract.
Qualifications
BS Degree in Mechanical Engineering, Electrical Engineering, Data Science, or a related field.
3+ years of experience specifically focused on Prognostics and Health Management (PHM), predictive maintenance, or reliability engineering.
Expertise in PySpark and Python for large-scale data manipulation, ETL, and feature engineering.
Hands-on experience working with the Databricks platform for development, deployment, and dashboard creation.
Hands-on experience deploying and scheduling analytical workflows using Airflow DAGs.
Proficiency with version control using Git.
Deep understanding of anomaly detection, time-series forecasting, survival analysis, and ML frameworks (e.g., scikit-learn, TensorFlow, PyTorch).
Experience applying signal processing techniques (e.g., FFT, wavelet transforms, filtering) to raw sensor data.
Familiarity with deploying batch-processing or offline analytical scripts using tools like Docker, Apache Airflow, AWS/GCP data pipelines, or similar infrastructure.
Solid understanding of hardware mechanics, fatigue, degradation models, or failure modes (FMEA/FMECA).
Preferred Qualifications
Prior experience in the Automotive/ Aerospace sector.
Experience working with large-scale data storage and querying (SQL, Databricks, Spark, etc.)
Master s or Ph.D. in Mechanical Engineering, Electrical Engineering, Data Science, or a related field.