Embedded Software Developer (Automotive)

Candidate is an Embedded Software Developer with a focus on automotive applications and driver assistance systems. He possesses experience in developing software for radar-based systems and autonomous driving functions, including the implementation of Kalman filters and Machine Learning models. His expertise includes Reinforcement Learning for optimizing Adaptive Cruise Control (ACC) systems, as well as creating Unit Tests and working in Software-in-the-Loop (SIL) environments. He is proficient in C++, Python, and relevant automotive tools.

Implementation of a Kalman filter for vehicle state estimation using camera-based object detection and depth estimation. Development of a Machine Learning model with PyTorch for predicting collision parameters, including data processing and model training. Conception and implementation of a motion prediction model and a real-time criticality assessment algorithm for autonomous driving in a SIL environment (Python, C++, OpenCV, Gitlab). Development and acceleration of a Reinforcement Learning framework for optimizing and applying Adaptive Cruise Control (ACC) in simulation and real vehicles (C++, Python, Linux, Jira, ROS 2, Docker). Optimization of ACC functions based on comfort and system performance KPIs, with a performance improvement in 83% of test scenarios. Software development on the application layer for radar-based driver assistance systems using C++ and Python. Creation of Unit Tests based on software requirements for embedded systems.