Lead ML Engineer - Lane & Route Network Mapping

About the role

You will lead the research and delivery of production-grade neural models that extract and maintain vectorized lane and route networks for May Mobility's autonomy stack. You own the end-to-end mapping architecture that converts raw sensor data into reliable topological and semantic representations used by downstream planning and control systems. You will define the long-term technical roadmap for the lane mapping domain while mentoring engineers and establishing rigorous standards for performance and scalability. You will collaborate closely with perception, prediction, and policy teams to ensure that mapping outputs meet the real-world demands of autonomous navigation. You will evaluate and adapt state-of-the-art techniques, including foundation models and online map construction, to operate across diverse and evolving environments. You will establish data curation and auto-labeling pipelines that turn fleet data into high-quality training and evaluation sets for mapping models. You will own the metrics and validation frameworks that guarantee mapping robustness, temporal consistency, and safety across May Mobility's operational design domains.

Key facts

What you'll do

Lead the research, design, architecture, training and validation of advanced neural networks for vectorized mapping (e.g., MapTR), multi-camera BEV transformers, and multimodal fusion models to extract and model lane and route networks for both high-fidelity offline pipelines and real-time online mapping.

Architect, design, and implement a production-grade lane and route network mapping stack, ensuring high-performance integration with upstream and downstream modules like Perception, Behavior, Policy, and Prediction.

Drive major feature development from inception to deployment. This includes high-level architecture design, rigorous code reviews, automated testing, mentorship of junior engineers, and technical resolution.

Own the end-to-end data strategy for the mapping domain, specifically focusing on lane and route networks. You will define 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 and route network accuracy, temporal consistency, and scaling across diverse Operational Design Domains (ODDs).

Work independently with cross-functional teams to translate complex autonomy goals into clear software and system requirements.

Collaborate with ML and Autonomy engineers to ensure the seamless deployment and validation of mapping features to the vehicle fleet.

Stay at the research frontier by evaluating, adapting, and innovating cutting-edge techniques, including online vectorized HD map construction, end-to-end mapping models, and vision/fusion Foundation Models to deliver production-ready solutions.

Establish and maintain scalable data ingestion, processing, and versioning workflows that support continuous mapping improvements across the fleet.

Define and enforce software engineering best practices for mapping modules, including reproducibility, monitoring, and fault tolerance in production environments.

Partner with product and operations teams to align mapping capabilities with vehicle planning, safety analysis, and regulatory constraints.

Contribute to internal knowledge transfer by documenting methodologies, model behaviors, and failure modes for both technical and non-technical audiences.

Guide the selection and customization of simulation tools and data loops to validate mapping performance under rare and edge-case conditions.

Champion quality and safety by designing experiments that quantify uncertainty, robustness, and generalization for lane and route network outputs.

Requirements

Candidates most successful in this role typically hold the following qualifications or comparable knowledge or experience. You must have a Ph.D. or Master's degree in Computer Science, Electrical Engineering, Robotics, or a related field with a strong mathematical and engineering foundation. You must bring 7+ years of industry experience developing and deploying ML/DL models for mapping or computer vision at scale. You must demonstrate deep expertise in several of the following areas: vectorized mapping networks (e.g., MapTR), BEV-based scene representation, and temporal modeling; cross-modal calibration and fusion (e.g., Camera-to-LiDAR) within Bird's-Eye-View (BEV) unified representation spaces; and transformers or Graph Neural Networks (GNNs) applied to structured lane geometry and topological connectivity. You must have hands-on experience with production ML infrastructure, including data versioning, model versioning, distributed training, and deployment on embedded or cloud platforms. You must be proficient in designing experiments, defining metrics, and analyzing results for complex spatial and temporal modeling tasks. You must have strong experience with modern deep learning frameworks such as PyTorch or TensorFlow and with scientific Python for data analysis and model debugging. You must be comfortable working with large-scale datasets and pipelines that process sensor data from vehicle fleets. You must have excellent written and verbal communication skills to collaborate with multi-disciplinary teams and to clearly articulate technical trade-offs and design decisions. You must be able to work effectively in an agile, fast-paced product development environment and manage multiple priorities while maintaining rigorous standards for system performance and reliability.