Senior ML Engineer - Mapping Ann Arbor, MI

May Mobility is transforming cities through autonomous technology to create a safer, greener, more accessible world. Based in Ann Arbor, Michigan, May develops and deploys autonomous vehicles (AVs) powered by our innovative Multi-Policy Decision Making (MPDM) technology that literally reimagines the way AVs think. Our vehicles do more than just drive themselves - they provide value to communities, bridge public transit gaps and move people where they need to go safely, easily and with a lot more fun.

We’re building the world’s best autonomy system to reimagine transit by minimizing congestion, expanding access and encouraging better land use in order to foster more green, vibrant and livable spaces. Since our founding in 2017, we’ve given more than 500,000 autonomous rides to real people around the globe. And we’re just getting started. We’re hiring people who share our passion for building the future, today, solving real-world problems and seeing the impact of their work.

Join us.

The Autonomy Mapping & Localization group's mission is to provide our vehicles with world‑class spatial intelligence, semantic and topological mapping, and state estimation to model and navigate complex urban, suburban, and rural environments. We are looking for a Senior ML Engineer to join our team and build the next generation of our mapping and localization stack. As the Senior ML Engineer for Mapping, you will be at the forefront of this mission, building the production‑grade semantic and topological foundation that allows our vehicles to understand and navigate the world’s most challenging roads at scale.

• Implement and optimize production‑grade lane and route network mapping ML, ensuring high‑performance integration with the broader autonomy system.
• Research, train, and evaluate advanced neural architectures. This includes object detection, classification, segmentation, tracking, depth estimation, and 3D reconstruction to extract and model lane and route networks, alongside key semantic features (e.g., traffic signs, signals, and road markings), for automated mapping.
• Participate in rigorous code reviews, automated testing, and technical resolution.
• Develop data curation, auto‑labeling, and active learning pipelines.
• Develop evaluation scripts for lane and route network accuracy, and scaling across diverse Operational Design Domains (ODDs).
• Collaborate with ML and Autonomy engineers to ensure the seamless deployment and validation of mapping features to the vehicle fleet.

Candidates most successful in this role typically hold the following qualifications or comparable knowledge or experience:

• M.S. or Bachelor's degree in Computer Science, Electrical Engineering, Robotics, or a related field with a strong mathematical and engineering foundation.
• 5+ years of industry experience developing and deploying ML/DL models for mapping or computer vision at scale.
• Deep expertise in several of the following areas:
• Computer Vision Foundations:
  Object detection, classification, segmentation, tracking, depth estimation, and 3D reconstruction.
• Lane-level topology and connectivity, intersection modeling, and lane/road network graph construction.
• Vectorized mapping networks (e.g., MapTR), BEV-based scene representation, and temporal modeling.
• Self-supervised/semi-supervised and vision/fusion Foundation Models.
• Expertise in ML/DL development using PyTorch or Tensor Flow, including experience with synthetic data generation, data curation, and model/algorithm evaluations.
• Strong programming skills in Python and/or C++ with experience in modular software design and Linux-based development.
• Ph.D. in Computer Science, Electrical Engineering, Robotics, or a related field with a strong mathematical and engineering foundation.
• Strong understanding of HD maps, including lane and road network geometry modeling, connectivity, and semantic attributes.
• Experience with feature extraction and/or fusion from both street-level and overhead imagery.
• Expertise in ML optimization for real-time products with limited compute, such as quantization and pruning of large transformer models.
• A proven record of inventions…