Machine Learning Engineer: Perception Analytics

The SpringCube team curated the following job opportunity to help you in your job search. Explore the position below to find your next career move.

Company Overview

A rapidly growing technology company is bringing advanced artificial intelligence and autonomous systems into the physical world. The organization develops autonomous systems for heavy construction equipment, helping improve job-site safety, accelerate project schedules, and support critical infrastructure projects.

The team brings together experienced professionals from leading technology and autonomous systems companies, combining expertise in artificial intelligence, robotics, construction, and large-scale engineering. The organization has raised significant funding and has achieved fully autonomous excavator deployments in construction environments.

The organization is seeking a Machine Learning Engineer: Perception Analytics to develop advanced perception features that power customer-facing analytics platforms. This role goes beyond traditional data science by applying machine learning and perception technologies to solve real-world challenges involving construction sites, robotics, and physical-world data.

The successful candidate will work on problems such as measuring excavation productivity using LiDAR and camera data, adapting perception systems to generate useful job-site metrics, evaluating safety across large construction sites, and re-identifying objects across numerous camera views despite challenging conditions such as dust, changing lighting, and complex environments.

What You’ll Do

• Extend, modify, and adapt existing perception signals to support analytics requirements.
• Work directly with customers to define and scope what can be achieved using advanced perception systems on construction sites.
• Deploy machine learning models and analytics directly to fleets of autonomous machines.
• Develop fundamental perception capabilities that support customer-facing analytics platforms.
• Analyze sensor and perception data to identify opportunities for improved productivity, safety, and operational insights.
• Develop solutions for challenging real-world perception problems that may not be fully represented in simulation environments.

What We’re Looking For

• MSc or advanced degree in Computer Science, Robotics, or a related field.
• 4+ years of professional experience developing and deploying perception systems to production, ideally on robotic or embedded platforms.
• Strong hands-on experience with a machine learning framework such as PyTorch.
• Proficiency in Python and the ability to read and write at least one systems programming language such as C++ or Rust.
• Hands-on experience incorporating raw sensor data, including camera, LiDAR, and IMU data, into learned machine learning pipelines.
• Strong understanding of 3D geometry, sensor calibration, including camera intrinsics and extrinsics, coordinate transformations, and camera/image reprojection algorithms.
• Strong data analysis capabilities, including statistical characterization of sensor data, corner-case and anomaly detection, and evaluation methodology design.

Ways to Stand Out

• Experience working directly with customers to understand perception data and analytics requirements.
• Experience with the Rust programming language.
• Published research or technical work in leading venues such as ICRA, IROS, CVPR, ECCV, ICCV, CoRL, or RSS.

Other Aspects of the Role

• The position is based in the Bay Area.
• The successful candidate should have the ability to work onsite at the San Francisco office on a daily or weekly basis.

Disclaimer

SpringCube curates tech job listings from various company websites to support tech professionals globally.

1. No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.
2. No Client Relationship: This company is not a client of SpringCube unless stated.
3. To Apply: Click the Apply button to be redirected to the hiring company’s application page for this job.
4. No Liability: SpringCube is not liable for inaccuracies.