Senior Perception Engineer

Sourced from feeny.ai

Pronto AI builds production-deployed autonomous haulage systems for mining, quarrying, and construction operations. As a Senior Perception Engineer, you will develop computer vision and machine learning systems that let autonomous machines perceive and reason about the physical world. The role spans 3D perception, multi-sensor fusion, temporal modeling, and deployment of models on latency-sensitive robotic platforms. You will work onsite in San Francisco alongside AI research, robotics, and systems engineering teams.

• Design, train, and deploy ML models for perception in autonomous systems
• Develop algorithms for object detection, classification, segmentation, tracking, and scene understanding
• Build 3D perception and geometric reasoning systems using cameras, LiDAR, radar, and other sensors
• Develop multi-sensor and multi-modal fusion approaches
• Build temporal models for objects, motion, trajectories, and environmental change
• Improve perception robustness under occlusion, sensor noise, and edge cases
• Build data, training, evaluation, and experimentation pipelines
• Define metrics connecting offline model performance to real-world behavior
• Optimize perception models for latency, compute, memory, and power constraints
• Diagnose deployed-system failures and drive improvements across models, data, and architecture

• 3-5 years of experience with perception systems, computer vision, and machine learning models
• Strong software engineering skills in Python and/or C++
• Experience developing perception systems for autonomous vehicles, robotics, drones, or industrial automation
• Experience with camera, LiDAR, radar, IMU, or other robotic sensor modalities
• Experience with multi-modal or multi-sensor architectures
• Knowledge of 3D geometry, coordinate transformations, calibration, localization, or state estimation
• Experience deploying ML models into real-time or safety-critical systems
• Experience optimizing models for latency, compute, memory, or power constraints
• Experience with large-scale perception datasets and training infrastructure
• Experience taking research ideas from experimentation through deployment on physical systems

• Publications or significant research contributions in computer vision, machine learning, or robotics