Back

KOSTAL Automobil Elektrik GmbH & Co. KG

In this fast paced business world, we have been guided by our values for more than a century. Success for us is not measured quarterly - we think for generations. We develop and manufacture electronic and mechatronic modules and thus shape the future of the automobile. As international family enterprise, based in Germany, Lüdenscheid, we run 64 locations in 22 countries on 5 continents in all business areas. In 2024, 20,400 employees generated a turnover of €5.1 billion provisionally, of which KOSTAL Automobil Elektrik accounted for €4.2 billion or 82%. We invest more than €200 million in research and development every year. Our products are built into every second car worldwide. We are shaping electromobility with over 5.5 milion onboard chargers in the field. We are the world market leader in the steering column modules, shift-by-wire modules and door control units, each with a market share of over 30%.
27/04/2026
Full time
Machine Learning Engineer / Edge-ML Automotive (m/w/d/kA)
KOSTAL Automobil Elektrik GmbH & Co. KG Dortmund, Germany
We are the KOSTAL Group, a globally operating, independent family business headquartered in Germany, developing and producing technologically sophisticated electronic and mechatronic products. More than 20,000 employees work flexibly, competently, and with a customer-centric approach at 64 locations in 22 countries. The KOSTAL Automotive Electrical division develops and produces power electronics for electromobility, control units for comfort electronics, and user interfaces ranging from turn signal switches to touchscreens. Job description Development of robust ML algorithms for intent/gesture recognition based on vehicle-side sensor data (e.g., UWB radar), including real-time inference on edge ECUs. End-to-end ownership of the ML pipeline: data acquisition on the prototype vehicle, ground truth/labeling, feature engineering, model training (PyTorch), experiment tracking (MLflow), model versioning and ensuring reproducibility Edge deployment:...