About the Role
We are a team of high-output generalists where ML and systems engineering converge to push autonomy performance forward. As a Senior Perception ML Data Infrastructure Engineer, you will own the critical bridge between our autonomous vehicle hardware, our human labeling operations, and our ML models.
You will take ownership of our core native perception data platform. This is not a standard web development role; the stack is deeply adjacent to our core robotics infrastructure. You will be dealing with massive, dense 3D point clouds at a scale that pushes the boundaries of industry state-of-the-art, alongside complex sensor parsing, pipeline propagation, and rigid performance constraints. You will operate in highly ambiguous environments, inheriting complex systems, establishing strict API boundaries, and building the "good enough, fast enough" infrastructure that guarantees our ML models learn from high-quality data.
Design and advance systems that:
- Render and manipulate massive, multi-modal sensor datasets (Lidar, Camera, Radar) efficiently in UI environments.
- Parse raw sensor data and manage complex data pipeline propagation between onboard hardware logs and offboard visualization.
- Enforce strict data validation and annotation constraints to prevent upstream labeling errors from polluting downstream ML pipelines.
- Create seamless, resilient API boundaries between our ML data pipelines and our Ground Truth/Data Platform infrastructure.
Tailor Your Impact:
- The Critical Path Owner: You will step into a complex, evolving ecosystem, quickly bring order to ambiguity, unblock critical operational bottlenecks, and architect sustainable long-term solutions that empower the entire Autonomy organization.
- High-Velocity Impact: You optimize the engineering lifecycle for autonomy progress. You know the exact trade-off between over-engineering a system and deploying a highly performant, pragmatic integration that keeps our data pipelines flowing.
About the work
You’ll solve autonomy’s hardest data bottlenecks through systems rigor and infrastructure excellence:
- Architect Core Data Platforms : Take formal technical ownership of our native, C++ based perception data visualization and annotation platforms.
- Optimize 3D Rendering & Robotics Data: Solve deep performance bottlenecks related to rendering next-generation, high-density Lidar point clouds and multi-camera projections in real-time.
- Defensive Engineering: Build robust data validation layers that catch sensor calibration errors, synchronization failures, and human labeling mistakes before they enter the ML training loop.
- Cross-Functional Leadership: Act as the technical bridge between ML, Data and Infrastructure engineers, and labeling operations.
About You
- BS/MS in Computer Science