ML Engineer, II - Road & Lane

Hands‑on experience developing ML models for perception tasks such as lane detection, road surface modeling, multi‑camera fusion, or related geometry estimation.

Strong understanding of camera calibration, multi‑sensor alignment, and projection between image and BEV spaces.

Proficiency in Python and PyTorch, with experience writing production‑quality machine learning code.

Experience training models on large datasets and using scalable compute environments.

Understanding of relevant ML architectures, such as CNNs, transformers, and BEV‑focused perception networks.

Ability to analyze model performance metrics, debug failure cases, and iterate effectively.

Develop and train computer vision and deep learning models for road‑lane detection using monocular and multimodal sensor data (camera, LiDAR, radar).

Build 3D road surface and lane geometry models in BEV space and integrate them into Torc’s autonomy pipeline.

Analyze model performance, identify corner cases, and improve robustness under diverse environmental and long‑tail conditions.

Develop and optimize large‑scale data processing workflows, including annotation, pseudo‑labeling, and data augmentation.

Implement scalable training and evaluation pipelines for lane perception models.

Own deployment-focused work to optimize models for real‑time execution on automotive‑grade hardware.

As a Machine Learning Engineer II – Road & Lane, you will help develop next‑generation models that estimate road surfaces, lane geometry, and lane topology within Torc’s autonomy stack. You will work closely with perception, mapping, and planning teams to deliver high‑quality, production‑ready lane perception models that enable safe and reliable autonomous trucking.