ADAS Perception Engineer - Lane Detection / Departure Warning

ADAS Perception Engineer - Lane Detection / Departure Warning

Our client, a leading Semicon/automotive technology company, is looking for an ADAS Perception Engineer to design, implement, and validate a camera-based lane detection and tracking system for an Advanced Driver Assistance System.

This is a 12-month contract based in Munich, working 3 days per week onsite.

What you will be doing

• Analysing requirements and defining system architecture for a front-camera-based lane detection function, including inputs, outputs, latency/accuracy targets, and ODD
• Designing and training neural networks (segmentation-based, anchor-based, or row-classification-based architectures such as LaneNet, SCNN, UFLD, PolyLaneNet, or transformer-based approaches) for lane marking/boundary detection
• Implementing lane tracking across frames (Kalman filter, particle filter, or learned temporal models) to ensure stable, jitter-free lane estimates and handle occlusion, worn markings, or missing lanes
• Fitting and maintaining a lane geometry model (clothoid/polynomial curve fitting) and estimating vehicle position/heading relative to the lane
• Developing lane departure warning logic, including time-to-lane-crossing estimation, threshold logic, driver intent filtering, and warning triggering strategy
• Integrating camera calibration (intrinsic/extrinsic) and inverse perspective mapping into the pipeline
• Optimising models for embedded/automotive-grade hardware (quantization, pruning, TensorRT/embedded inference frameworks) to meet real-time constraints
• Building datasets, defining annotation guidelines, and driving data collection strategy across diverse conditions
• Validating against relevant standards (e.g. Euro NCAP LDW/LKA test protocols) and defining test/validation KPIs
• Collaborating with vehicle integration teams and supporting HIL/vehicle-level testing

What we are looking for

• Strong background in computer vision and deep learning, particularly semantic segmentation, keypoint detection, or curve-fitting-based lane detection
• Proficiency in Python and PyTorch
• Solid understanding of classical CV techniques: camera calibration, homography/IPM, edge detection, Hough transforms
• Experience with lane/object tracking algorithms (Kalman filter, EKF, particle filters) and temporal fusion
• Familiarity with curve/polynomial or clothoid-based lane modelling
• Experience deploying models on embedded/automotive compute
• C++ proficiency for production/embedded implementation
• Understanding of ADAS software architecture and real-time constraints
• Familiarity with automotive standards: Euro NCAP LDW/LKA test protocols, ASPICE process awareness
• Experience with lane detection datasets (TuSimple, CULane, BDD100K, or proprietary OEM datasets)

In accordance with local employment laws, applicants must have current, valid authorisation to work in Germany at the time of application. We are unable to sponsor employment visas for this role. Applications from individuals without existing work authorisation for Germany cannot be considered.

If this sounds interesting and you'd like to learn more, click the link below to apply or email me with a copy of your CV on [email protected]

By applying to this role you understand that we may collect your personal data and store and process it on our systems. For more information please see our Privacy Notice (https://eu-recruit.com/about-us/privacy-notice/)