Scientist / Research Eng General

.entry-header Location: Dearborn, Michigan Type: Contract Job #105483 StartFragment Prognostics Research Engineer Location: Dearborn, MI (Hybrid – 4 Days Onsite) Industry: Automotive Research & Connected Vehicle Technology Education: Master’s Degree Required | PhD Preferred About the Role Are you passionate about using data science, machine learning, and engineering principles to solve complex vehicle reliability challenges? Our client is seeking a Prognostics Research Engineer to develop next-generation predictive maintenance and health-monitoring solutions for connected vehicles. In this role, you will leverage large-scale vehicle data, advanced analytics, physics-based modeling, and machine learning techniques to predict component degradation and estimate Remaining Useful Life (RUL) across both electric and internal combustion engine (ICE) platforms. This is a unique opportunity to work at the intersection of data science, vehicle diagnostics, embedded software, signal processing, and advanced research, helping bring innovative prognostic technologies from concept to production vehicles. What You’ll Do Develop predictive maintenance and prognostic algorithms for vehicle systems and components. Build and deploy Remaining Useful Life (RUL) models using machine learning and physics-based approaches. Analyze large-scale connected vehicle and telemetry data to identify early indicators of component degradation. Design and implement signal processing pipelines for high-frequency sensor data. Develop fault detection and anomaly detection algorithms for real-time vehicle monitoring. Apply advanced statistical methods including PCA, ANOVA, clustering, neural networks, causal inference, and multivariate analysis. Create and validate models using MATLAB, Simulink, Python, and other analytical tools. Optimize and deploy predictive models into embedded C++ environments for production vehicle applications. Perform Hardware-in-the-Loop (HIL) testing and validation activities. Collaborate with engineering subject matter experts across EV, powertrain, controls, software, and vehicle systems teams. Utilize cloud platforms and big-data technologies to process and analyze large-scale fleet data. Required Qualifications Master’s Degree in Mechanical Engineering, Electrical Engineering, Computer Science, Computer Engineering, Physics, Mathematics, or a related field. 4+ years of experience applying advanced statistical and machine learning techniques. 3+ years of experience with Python and SQL. Experience with: Machine Learning and Data Science MATLAB and Simulink Embedded Controls and Diagnostics Digital Signal Processing (DSP) Sensor Processing C++ Programming Vehicle or System Modeling Strong analytical, communication, and problem-solving skills. Preferred Qualifications PhD in a related engineering or scientific discipline. Experience with: Prognostics and Health Management (PHM) Predictive Maintenance Remaining Useful Life (RUL) Modeling Dynamic Systems, Controls, or Robotics Connected Vehicle Data Analytics Automotive Diagnostics Spark, Hadoop, R, and Open-Source Data Science Technologies ATI and ETAS Calibration Tools Automotive Software Development and Embedded Systems Technical Skills Programming & Analytics Python SQL C++ MATLAB Simulink Data Science & Machine Learning Neural Networks PCA ANOVA Clustering Causal Inference Time Series Analysis Multivariate Analysis Gaussian Regression Cloud & Big Data Google Cloud Platform (GCP) Spark Hadoop Automotive & Controls Embedded Systems Vehicle Diagnostics Signal Processing HIL Testing Prognostics & Health Monitoring Why Apply? This role offers the opportunity to work on cutting-edge connected vehicle technologies that directly impact the future of automotive reliability, predictive maintenance, and intelligent vehicle health monitoring. You’ll collaborate with industry experts while helping develop innovative features that move from research concepts into production vehicles. Schedule: Hybrid – 4 days onsite per week in Dearborn, MI. #LI-PS1 #INDOEM .entry-content .clear #post-##