Job
Description
Job Requirements We are seeking an experienced Embedded Validation Engineer with expertise in Advanced Driver Assistance Systems (ADAS), perception algorithms, dSPACE, and NVIDIA platforms . The ideal candidate will be responsible for validating embedded software, testing perception models, and ensuring the robustness of ADAS functionalities across different hardware platforms. Key Responsibilities Embedded Software Validation: Develop and execute test plans, test cases, and test automation for ADAS and perception systems. Validate embedded software running on dSPACE Scalexio, NVIDIA Jetson, and other automotive platforms. Conduct Software-in-the-Loop (SiL), Hardware-in-the-Loop (HiL), and Vehicle-level testing. Perform real-time debugging, issue analysis, and defect tracking. ADAS & Perception System Testing Validate sensor fusion, object detection, lane detection, and path planning algorithms. Ensure performance benchmarking of camera, LiDAR, and radar-based perception models. Work closely with AI/ML teams to validate deep learning-based perception models. DSPACE & NVIDIA Platform Expertise Work with dSPACE Scalexio, ControlDesk, and AutomationDesk for validation tasks. Validate and optimize CUDA, TensorRT, and ROS-based perception models on NVIDIA Jetson. Develop custom test frameworks and automation scripts for validation. Cross-functional Collaboration & Documentation Work closely with software developers, system architects, and hardware engineers. Provide technical reports, validation summaries, and defect analysis documentation. Participate in customer discussions and requirement analysis. Work Experience 6-8 years of experience in embedded validation, preferably in ADAS and perception systems. Strong hands-on experience with dSPACE Scalexio, NVIDIA Jetson (Xavier/Orin), and MATLAB/Simulink. Experience with HiL/SiL/MiL testing and validation tools. Expertise in Python, C++, MATLAB scripting, and automation frameworks. Familiarity with AUTOSAR, ROS, and functional safety standards (ISO 26262). Experience with CANoe, CANalyzer, and automotive communication protocols (CAN, Ethernet, LIN). Strong debugging skills with JTAG, debuggers, and real-time OS profiling tools. Preferred Qualifications Experience in AI/ML model validation and deep learning-based perception. Hands-on with Docker, TensorRT, OpenCV, and CUDA optimizations. Show more Show less
