Software Engineer, Geometric Generation

Aurora•Mountain View, CA

5d•Hybrid

About The Position

Aurora’s Map Build Geometric Generation team is hiring a Software Engineer to build the 3D spatial foundation that powers the Aurora Driver. The role owns algorithms that process millions of miles of lidar logs into automated offline maps, addressing speed and scaling challenges as Aurora expands to new routes. The work includes developing robust geometric map-generation systems and improving the runtime and scalability of the distributed map-build pipeline. The position is expected to work from an Aurora office at least three days per week, with some roles requiring up to five days per week based on operational needs.

Requirements

Bachelor’s, master’s, or PhD in Computer Science, Robotics, Electrical Engineering, or a related field, or equivalent practical experience.
At least 3 years of professional software development experience in C++.
Hands-on experience with 3D geometry and point-cloud processing, such as registration (ICP or scan matching), pose-graph or nonlinear least-squares optimization, surface reconstruction, or lidar-based SLAM/mapping.
Strong grasp of linear algebra, spatial transforms, numerical optimization, and probability.
Experience debugging and improving data quality across large datasets or pipelines.

Nice To Haves

Experience building HD maps or map-building systems for autonomous vehicles or robotics.
Experience applying computer vision or semantic segmentation to geometric problems.
Experience with large-scale distributed data processing, such as Beam, Spark, or batch compute on AWS, and performance optimization.
Familiarity with geospatial concepts such as coordinate frames, map projections, and tiling schemes.
Proficiency in Python.

Responsibilities

Design, implement, and own geometric map-generation algorithms, including sensor optimization, large-scale pose-graph optimization, and multimodal alignment.
Identify and build systems resistant to failure modes; root-cause issues and deliver algorithmic fixes with measurable success criteria.
Improve runtime and scalability of large-scale distributed map-build pipeline stages.
Collaborate with neighboring teams to define data contracts and integration requirements.