.png){kind=logo}
kunj Golwala
Junior Robotics Perception Engineer specializing in autonomous navigation and robot learning
Connect with kunj
kunj already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Robotics software/perception engineer with production AMR experience at Symbotic, building a real-time SKU case re-identification pipeline used in high-volume Walmart/Target warehouse operations. Strong in ROS2 + Docker deployments on Jetson (TensorRT quantization) and system-level performance debugging, including cutting inference latency from ~13s to ~2s through architecture changes. Also has lab experience integrating SLAM/MPPI/behavior trees for rule-compliant navigation and distributed perception-to-UR5e manipulation systems (MoveIt/ros_control) with multi-camera sensing and 3D reconstruction.
Experience
Education
Key Strengths
- End-to-end ownership of production robotics perception (model to on-robot deployment)
- Large-scale visual re-identification for 20,000+ SKUs under occlusion/variable lighting
- System-level performance debugging (camera-to-inference profiling) and architecture optimization
- Major latency reduction via container consolidation, multithreading, and embedding caching (reported ~70% reduction; 13s to ~2s inference)
- Deep ROS1/ROS2 integration across perception, planning, and manipulation stacks
- Real-time navigation/SLAM debugging and tuning (keyframe window/ICP optimization; stabilizing pose drift)
- Improved tracking robustness by adding ego-motion compensation using wheel odometry
- Distributed multi-machine robotics integration using ROS topics/services/actions with consistent TF and calibration
Discover more candidates like kunj
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent