On-Site Edge Perception Engineer for Real-World Robots

Kovari; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Kovari is seeking a senior perceptual systems engineer to own our perception stack end to end. You will work on sensor fusion, localization, mapping, and scene understanding for deployed robots in real-world environments.

You will optimize real-time perception on edge hardware, debug field failures, and drive improvements in models and data. This role requires hands-on robotics experience and strong C++/Python skills, with on-site collaboration in San Francisco.

Qualifications

• Strong background in computer vision and 3D geometry.
• Experience shipping perception on real robots or vehicles.
• Experience with SLAM, state estimation, or multi-sensor fusion.
• Proficiency in C++ and Python; PyTorch for learned components.
• Experience with edge inference (TensorRT, ONNX Runtime, or similar).

Responsibilities

• Build sensor fusion across cameras, depth, IMU, and proprioception.
• Own calibration, time synchronization, and sensor health monitoring.
• Develop localization, mapping, and scene understanding for real environments.
• Build detection, segmentation, and 3D representations for manipulation and navigation.
• Optimize perception for real-time inference on edge hardware.
• Debug field failures and drive fixes back into models and data.

Skills

Computer vision

3D geometry

C++

Python

PyTorch

Edge inference

SLAM / multi-sensor fusion

Field robotics

Bias toward action

Tools

TensorRT

ONNX Runtime

Job description

Kovari is seeking a senior perceptual systems engineer to own our perception stack end to end. You will work on sensor fusion, localization, mapping, and scene understanding for deployed robots in real-world environments.

You will optimize real-time perception on edge hardware, debug field failures, and drive improvements in models and data. This role requires hands-on robotics experience and strong C++/Python skills, with on-site collaboration in San Francisco.