Source description
About the role
Architect Multi-Modal Vision Systems: You will design and train models that fuse 2D inputs with 3D geometry to solve complex grasping and scene understanding tasks.
Lead End-to-End Model Deployment: You will own the transition from research to reality. This includes model graph optimization, quantization (TensorRT), and runtime integration to ensure low-latency inference on our edge compute hardware (NVIDIA Orin).
Drive Technical Excellence: As a senior member of the team, you will conduct rigorous code reviews, mentor junior engineers, and contribute to the strategic perception roadmap.
Own the Data Strategy: You will take ownership of our existing labeled dataset and pipeline. You will identify bottlenecks, improve data quality, implement active learning strategies to systematically resolve edge cases and improve model robustness.
Ensure Production Reliability: You will write high-performance production code (Python/C++) to seamlessly integrate perception outputs into the broader robotic control stack, prioritizing safety and system stability.
More at Pickle Robot
Related open roles
Software Engineering Manager, Motion Planning
United States · Hybrid
Senior Electrical Engineer
United States · Hybrid
Backend Software Engineer – Software Architecture
United States · Hybrid
Backend Software Engineer – Human-Robot Interaction
United States · Hybrid
DevOps Engineer
United States · Hybrid
Senior Perception Software Engineer
United States · Hybrid
