Staff, ML Engineer - Road & Lane Detection

Torc Robotics is a leader in autonomous driving technology, focused on developing software for automated trucks. The Staff Machine Learning Engineer will lead model development for road and lane detection, focusing on deep learning architectures and data-driven approaches to improve perception accuracy and robustness.

Responsibilities:

• Own the model roadmap for Road & Lane Detection within the Model Dev ML org — from concept through production-grade model maturity
• Research, design, and train advanced neural architectures (e.g., multi-camera BEV transformers, LiDAR-vision fusion models, topological lane graph networks) to detect, segment, and model road structures and lane connectivity
• Lead data strategy for this domain — defining data curation, labeling policies, and active learning pipelines to capture long-tail scenarios (e.g., occlusions, complex merges, construction zones)
• Develop robust metrics and evaluation frameworks for lane and road geometry accuracy, temporal consistency, and cross-domain generalization
• Advance foundational capabilities such as self-supervised pretraining, synthetic-to-real adaptation, and temporal modeling for road and lane understanding
• Drive large-scale experiments — designing, running, and analyzing results from distributed training workflows and ablations to identify scalable improvements
• Collaborate with other model dev/perception teams to ensure model coherence and interface consistency
• Mentor engineers and scientists, setting best practices for model training, evaluation, and code quality
• Stay ahead of the research frontier by evaluating and adapting emerging techniques (e.g., BEV-based large models, vectorized map prediction, lane graph transformers) to production-grade perception