Lead ML Engineer - Lane & Route Network Mapping
May Mobility · USA - Remote
About this role
**May Mobility — Lead ML Engineer (Lane & Route Network Mapping)** May Mobility is transforming cities through autonomous technology to create a safer, greener, more accessible world. Based in Ann Arbor, Michigan, we develop and deploy autonomous vehicles (AVs) powered by our Multi-Policy Decision Making (MPDM) technology. The Autonomy Mapping & Localization group provides world-class spatial intelligence, semantic/topological mapping, and state estimation to model and navigate complex urban, suburban, and rural environments. We’re hiring a **Lead ML Engineer** to architect the next generation of our mapping and localization stack—building a production-grade semantic and topological foundation for lane and route networks. --- ## Essential Responsibilities - Lead research, design, architecture, training, and validation of advanced neural networks for **vectorized mapping** (e.g., MapTR), **multi-camera BEV transformers**, and **multimodal fusion** to extract and model lane/route networks for both **offline** and **real-time online** mapping. - Architect, design, and implement a **production-grade lane and route network mapping stack**, ensuring high-performance integration with upstream/downstream modules (Perception, Behavior, Policy, Prediction). - Drive major feature development from inception to deployment: architecture, rigorous code reviews, automated testing, mentorship, and technical resolution. - Own the end-to-end **data strategy** for mapping—defining data curation, auto-labeling, synthetic data, and active learning pipelines to capture and resolve long-tail scenarios. - Develop robust **metrics and evaluation frameworks** for lane/route accuracy, temporal consistency, and scaling across diverse Operational Design Domains (ODDs). - Work independently with cross-functional teams to translate autonomy goals into clear software/system requirements. - Collaborate with ML and Autonomy engineers to ensure seamless deployment and validation of mapping features to the vehicle fleet. - Stay at the research frontier by evaluating and innovating cutting-edge techniques (e.g., online vectorized HD map construction, end-to-end mapping models, vision/fusion foundation models) for production-ready solutions. --- ## Qualifications and Experience **Required** - Ph.D. or Master’s degree in Computer Science, Electrical Engineering, Robotics, or related field with strong mathematical/engineering foundation. - **7+ years** industry experience developing and deploying ML/DL models for mapping or computer vision at scale. - Deep expertise in several areas, including: - Vectorized mapping networks (e.g., MapTR), BEV-based scene representation, temporal modeling - Cross-modal calibration/fusion (e.g., Camera-to-LiDAR) within BEV unified representation spaces - Transformers and/or Graph Neural Networks (GNNs) for structured lane geometry and topological connectivity - Lane-level topology/connectivity, intersection modeling, lane/road network graph construction - Computer Vision foundations: detection, classification, segmentation, tracking, depth estimation, 3D reconstruction - Strong understanding of HD maps (lane/road geometry modeling, connectivity, semantic attributes). - ML/DL development expertise using **PyTorch or TensorFlow**, including distributed training, synthetic data generation, large-scale dataset handling, and data curation. - Strong programming skills in **Python and/or C++**, with modular software design and Linux-bas
Listing freshness
CronJobs last confirmed this listing 15h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.