Machine Learning Engineer: Perception Analytics
HybridSan Francisco, California, United States
Job Summary
Develop perception algorithms for vehicle re-identification on massive construction sites and extend existing perception signals to drive customer-facing analytics platforms. Collaborate with customers to scope advanced perception capabilities and deploy models directly to fleets of machines. Incorporate raw sensor data from cameras, lidar, and IMUs into learned pipelines while applying 3D geometry and sensor calibration techniques. Requires an MSc in Computer Science or Robotics, four years of production perception experience, and proficiency in Python with systems languages like C++ or Rust. Based in the Bay Area with daily/weekly onsite availability at the SF office.
Required Qualifications
- MSc or advanced degree in Computer Science, Robotics, or a related field
- 4+ years of professional experience shipping perception systems to production (ideally on robotic or other embedded platforms)
- strong hands-on experience in a modeling framework (e.g. PyTorch)
- Proficient in Python
- comfortable reading and writing at least one systems language (e.g. C++, Rust)
- Hands-on experience incorporating raw sensor data (camera, lidar, IMU) into learned pipelines
- Solid grounding in 3D geometry
- sensor calibration (intrinsics/extrinsics)
- coordinate transforms
- camera/image re-projection algorithms
- Strong data analysis skills across statistical characterization of sensor data
- corner-case and anomaly discovery
- evaluation design
- Based in the Bay Area with the ability to be onsite at our SF office on a daily/weekly basis
Desired Qualifications
- experience with the Rust programming language
- Prior experience with object re-ID tasks
- Prior experience working with customers to understand perception data and analytics
- Published work in top-tier venues such as ICRA, IROS, CVPR, ECCV, ICCV, CoRL, or RSS
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.