Sherdil Niyaz
Planner Reasoning Engineer at Waymo
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolSherdil Niyaz is a Planner Reasoning Engineer with 11 years of experience building and shipping motion and behavior planning systems for autonomous vehicles, currently driving planner reasoning at Waymo after recent roles at Ford and Motional. He holds a CSE PhD from the University of Washington and combines deep research expertise in constrained motion planning and grasping with hands-on production engineering that has run on real cars. Sherdil has a strong robotics ML background—contributing to the well-known BerkeleyAutomation gqcnn repo by integrating grasp sampling and robot control nodes—and has translated prototypes into merged, on-vehicle code at companies like Nuro and Motional. He also cares about teaching and tooling, having modernized CS courses, built an autograding pipeline with GitHub Classroom, and earned top teaching evaluations. Comfortable across vision, search, projection, and planning stacks, he balances principled algorithms with pragmatic engineering to close the loop from papers to deployed systems. Based in the Bay Area, he blends academic rigor with product-driven impact and a knack for simplifying complex pipelines.
11 years of coding experience
8 years of employment as a software developer
PhD Computer Science, PhD Computer Science at University of WashingtonBS Electrical Engineering & Computer Science, BS Electrical Engineering & Computer Science at University of California, Berkeley
Github Skills (8)
computer-vision10
machine-learning10
robotics10
python10
ros10
deep-learning9
tensorflow8
caffe7
Programming languages (5)
Github contributions (5)
BerkeleyAutomation/gqcnn
May 2017 - Jun 2017
Python module for GQ-CNN training and deployment with ROS integration.
Role in this project:
ML Engineer
ML EngineerContributions:8 commits in 7 days
Contributions summary:Sherdil implemented and tested a Yumi robot control node for grasping tasks using the GQ-CNN model. They developed a grasp sampling node for the GQ-CNN, integrating it with camera intrinsics and object detection bounding boxes. The user further refined the grasping policy with minor changes and fixed merge conflicts within the codebase. Additionally, they worked on ROS node integrations and added data models for the robot's gripper.
roboticspythondeep-learningdeploymentmachine-learning
personalrobotics/eyerectoo_pupil
Oct 2017 - May 2018
Contributions:14 commits, 12 pushes, 1 branch in 7 months
uniprlinformatikatreus
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.