Senior Machine Learning Engineer - Mapping

General Motors Corporation; Sunnyvale (CA); Hybrid; USD 171,000 - 261,000; Full time

Benefits offered by this job

Hybrid work model

Relocation benefits

Health benefits

Job summary

General Motors is seeking a Senior Machine Learning Engineer to design and implement advanced mapping algorithms and geospatial data systems for scalable map reconstruction and maintenance. You will work on lanes, boundaries, road networks, and topology with ML-enhanced pipelines.

You will own end-to-end development, collaborating with perception, localization, and simulation teams, and deploying models in production with robust validation and quality checks.

Qualifications

• 3+ years of software engineering experience building production systems with a focus on mapping or geospatial algorithms.
• Strong foundation in geospatial and computational geometry concepts (coordinates, projections, spatial indexing, map matching, road networks).
• Hands-on ML/CV workflow in production — data curation, model training or fine-tuning, evaluation and deployment.
• Experience building large-scale distributed geospatial data pipelines for sensor data or maps.

Responsibilities

• Design and implement mapping algorithms for map reconstruction and maintenance (lanes, boundaries, road graphs).
• Develop geospatial data models for lane connectivity and road networks at intersections.
• Build and deploy large-scale geospatial pipelines processing sensor data into production map releases.
• Apply ML/CV models to automate feature extraction and map change detection in pipelines.
• Create automated quality, validation, and regression systems for geometry and topology checks.

Skills

Python

C++

Geospatial algorithms

Distributed systems

Education

BS in CS/GIS/EE/Robotics or related

MS in CS/GIS/EE/Robotics or related

Tools

PostGIS

GeoPandas

GDAL/OGR

S2/H3

OSM

GeoJSON

Job description

## Senior Machine Learning Engineer - MappingApply: Hybrid: Sunnyvale, California, United States of America: Remote - Washington: Austin, Texas, United States of America: Mountain View, California, United States of America: Full time: Posted Yesterday: JR-202620459**Job Description** **About the Team**Our Mapping organization is building national-scale, next-generation mapping systems that move beyond static HD maps toward automated, algorithmic and ML-assisted map reconstruction pipelines powered by onboard sensor data. These systems form a critical foundation for localization, perception, simulation, and autonomy at scale. ## The RoleWe are looking for a Senior Software Engineer to design and build the mapping algorithms and geospatial data systems behind automated map reconstruction and maintenance within our Mapping Engineering team.In this role, you will develop the algorithms and data models that reconstruct, conflate, validate, and maintain map primitives — lanes, lane connectivity, road network graphs, boundaries, traffic controls, and signs — from large-scale multi-modal sensor data. You will own the geometric and topological correctness of the map itself: how features are represented, how disparate sources are merged, and how errors are detected before they reach the vehicle.This is a hands-on individual contributor role with strong ownership. You will drive technical problems end to end, partner closely with Perception, Localization, and Simulation, and apply machine learning where it measurably improves accuracy, coverage, or automation rate. ## What You'll Do (Responsibilities)* Design and implement mapping algorithms for map reconstruction and maintenance — lane and boundary extraction, road network graph construction, map conflation and matching, geometry simplification, and topology validation.* Build and evolve geospatial data models for lane-level connectivity at intersections, road network graphs, and associated map attributes and restrictions.* Develop large-scale distributed geospatial pipelines that process sensor-derived and third-party road data into production map releases on a recurring cadence.* Apply machine learning and computer vision models — detection, segmentation, 3D reconstruction, BEV representations — to automate feature extraction and map change detection, and integrate them into production pipelines.* Build automated quality, validation, and regression systems that catch geometric, topological, and semantic map defects before release, with clear accuracy metrics.* Collaborate cross-functionally with Perception, Localization, Simulation, and Platform teams on interfaces, data contracts, and integration points.* Diagnose and resolve system-level issues spanning geospatial data pipelines, algorithms, models, and production workflows.* Contribute to design reviews, engineering best practices, and mentorship of engineers on the team. **Minimum Qualifications (Must-Have)*** 3+ years of software engineering experience building production systems, with a substantial portion focused on mapping, geospatial, or geometric algorithms.* Strong applied foundation in geospatial and computational geometry concepts — coordinate systems and projections, spatial indexing, geometry operations, map matching, and graph algorithms on road networks.* Demonstrated experience designing geospatial data models and working with road network or map data structures (lanes, segments, intersections, topology).* Hands-on experience with machine learning or computer vision workflow in production — dataset curation, model training or fine-tuning, evaluation, and deployment.* Experience building large-scale distributed data pipelines for geospatial or sensor data.* Proficiency in Python and C++.* BS or MS in Computer Science, GIS, Electrical Engineering, Robotics, or a related technical field, or equivalent industry experience.* Ability to own ambiguous, well-scoped technical problems end to end and drive them to production. ## Preferred Qualifications (nice to have)* Experience with HD maps, localization, perception, or robotics systems, particularly in autonomous driving or mobile robotics.* Hands-on experience with 3D geometry, multi-view geometry, point cloud processing, or SLAM.* Familiarity with AV sensor data (camera, lidar, radar) and real-world data challenges such as noise, drift, and long-tail scenarios.* Experience with map conflation, change detection, or automated map QA at national or global scale.* Experience with geospatial tooling and formats (PostGIS, GeoPandas, GDAL/OGR, S2/H3, OSM, GeoJSON).* Experience deploying ML models into production pipelines with monitoring, validation, and iteration loops.* Experience mentoring engineers or acting as a technical lead on a project.* 3+ years of software engineering experience building production systems, with a substantial portion focused on mapping, geospatial, or geometric algorithms. *Compensation*: The compensation information is a good faith estimate only. It is based on what a successful applicant might be paid in accordance with applicable state laws. The compensation may not be representative for positions located outside of the California Bay Area.* The salary range for this role is $170,600.00 to $261,300.00. The actual base salary a successful candidate will be offered within this range will vary based on factors relevant to the position.* Bonus Potential: An incentive pay program offers payouts based on company performance, job level, and individual performance. *Benefits:** Benefits: GM offers a variety of health and wellbeing benefit programs. Benefit options include medical, dental, vision, Health Savings Account, Flexible Spending Accounts, retirement savings plan, sickness and accident benefits, life insurance, paid vacation & holidays, tuition assistance programs, employee assistance program, GM vehicle discounts and more. This role is categorized as hybrid. This means the selected candidate is expected to report to a specific location at least 3 times a week {or other frequency dictated by their manager}.Relocation benefits are available for candidates who qualify under company policy.