Scientist-Research Engineer (ML)

Job Summary

We are seeking a highly motivated Scientist / Research Engineer to develop and deploy advanced prognostics and predictive maintenance solutions for vehicle systems. The ideal candidate will leverage data science, machine learning, physics-based modeling, and signal processing techniques to predict component degradation and estimate Remaining Useful Life (RUL) for automotive applications.

Key Responsibilities

• Develop prognostic and predictive maintenance algorithms using vehicle and connected vehicle data.
• Build machine learning and physics-informed models to analyze component health and degradation.
• Process and analyze large datasets using Python, SQL, and cloud platforms.
• Develop fault detection and anomaly detection solutions for vehicle systems.
• Perform modeling and simulation using MATLAB/Simulink.
• Collaborate with cross-functional teams to deploy solutions into production vehicles.
• Support embedded software implementation in C++ environments.

Required Skills

• Python
• SQL
• C++
• Data Science & Machine Learning
• MATLAB / Simulink
• Algorithms & Statistical Analysis
• Google Cloud Platform (Google Cloud Platform) or other cloud environments
• Signal Processing (DSP)
• Predictive Analytics & Prognostics

Required Qualifications

• Master''s degree in Mechanical Engineering, Electrical Engineering, Computer Science, Computer Engineering, Mathematics, Physics, or related field.
• 4+ years of experience applying statistical and machine learning techniques.
• 3+ years of experience with Python and SQL.
• Experience with predictive modeling, sensor data analysis, and vehicle diagnostics.
• Strong analytical and problem-solving skills.

Preferred Qualifications

• PhD in a related technical field.
• Experience in Automotive, Connected Vehicle, EV, Controls, Robotics, or Prognostics & Health Management (PHM).
• Knowledge of Spark, Hadoop, ATI, ETAS, and embedded systems.
• Experience with machine learning techniques such as PCA, ANOVA, Clustering, Neural Networks, Time Series Forecasting, and Causal Inference.