Position: Cloud Prognostics Engineer
Required Skills & Experience
-Systems Engineering experience with data expertise
-Automotive experience
-Intro/junior level experience with Python and PowerBI. Ability to handle big data & analyze data to create visuals
-C++, MATLAB and Simulink. Ability to model using MATLAB Simulink and generate C++ code for prognostics degradation models.
-Cloud experience
-Experience with mechanical hardware and DNR
-Master's Degree
Job Description
The Cloud Prognostics Engineer will spend 50% of their time on systems engineering, and the remaining 50% on data analysis, requirements, testing and validation.
The engineer must be capable of defining system boundaries, establishing logical and physical architectures, mapping interface definitions, and allocating prognostic functions across different physical components (e.g., deciding which calculations run on a local sensor, the central gateway, or the cloud). Using MATLAB and Simulink to design control logic, model physical system dynamics, and auto-generate production-grade, highly efficient C++ code. The engineer must understand how to configure solver settings, manage data types (fixed-point vs. floating-point), and ensure the generated code integrates seamlessly into automotive operating systems. The engineer must know how to select, place, and calibrate physical sensors (like accelerometers and strain gauges) on prototype vehicles, capture high-fidelity physical data, and prepare those datasets for algorithmic analysis. The engineer must design the system to comply with ISO 26262 (determining ASIL ratings and designing fail-safe/fail-degraded states) and ISO 21434 to ensure the prognostic pipeline is secure from edge to cloud. Designing optimized network communication and transport protocols. This includes using Gherkin to model behavioral scenarios of cloud-to-vehicle modem communications, designing dynamic data-triggering strategies (e.g., only uploading detailed vibration spectra when an anomaly threshold is crossed), and optimizing payload serialization to minimize data transmission costs. The engineer must know how to map raw binary hex logs back to human-readable physical values using database-defined translation tables (such as DBC or ARXML databases). Advanced capability in eliciting, documenting, and tracing complex, multi-disciplinary requirements using Application Lifecycle Management (ALM) tools like Jama, Jira, and Team Center. The engineer must ensure seamless traceability from high-level customer experience goals down to software requirements, hardware interfaces, and Design Verification Plans (DVP). In-depth knowledge of automotive communication protocols, including CAN, LIN, and Automotive Ethernet. The engineer must be highly skilled in integrating prognostic software applications onto central gateway modules managing signal routing, and resolving network timing or priority conflicts during physical system integration. Practical application of Robust Engineering principles, specifically creating Parameter Diagrams (P-Diagrams) to identify system inputs, desired outputs, error states, control factors (design parameters), and noise factors (environmental, wear, manufacturing tolerances). This ensures the algorithm is tuned to be highly robust against false positives. Ability to connect technical engineering metrics (such as algorithm accuracy, false-alarm rates) to real-world quality indicators like Net Promoter Score (NPS), JD Power ratings, and Vehicle Repair rates. The engineer must collaborate cross-functionally with divisions to integrate prognostic alerts into user-friendly smartphone applications, ensuring a seamless, anxiety-free service scheduling experience for vehicle owners.