Maymobility Robotics Engineer II at May Mobility to train, integrate, and test ML models for autonomous vehicle software. Optimize on-vehicle software and coordinate real-world testing to ensure reliability and performance.
Responsibilities
Train, Integrate and Test Machine Learning models for on-vehicle Autonomy software
Optimize and Monitor on-vehicle software for maximum reliability and minimum latency
Coordinate and execute on-vehicle tests to validate performance of Autonomous Vehicle software in real-world scenarios
Diagnose and root-cause issues reported by commercial operations through the May Field Response process
Design and oversee data collection strategies to address ML model deficiencies
Develop tools and visualizations to enable support engineers to analyze performance of behavior and control subsystems from field data
Qualification
Bachelor's degree in RoboticsFunctional understanding of lidarFamiliarity with common PerceptionProficiency with hard example mining
Required
Candidates most successful in this role typically hold the following qualifications or comparable knowledge or experience:
2+ years experience with robotics software for physical systems in a commercial environment
Bachelor's degree in Robotics, Computer Science, Computer Engineering, or a field that requires a strong mathematical and/or engineering foundation (e.g. physics, aerospace engineering)
Basic understanding of ML model concepts such as training, architectures, and data selection
Functional understanding of lidar, camera and/or radar perception systems and their hardware interfaces
Strong programming skills in C/C++/Python in a Linux environment
Functional proficiency with Software concepts such as memory management, threading, databases and networking
Familiarity with standard development tools such as git, valgrind, and gdb
Familiarity with common Perception, Planning and Foundation model concepts in Autonomous Driving.
Experience deploying ML models to resource-constrained hardware
Experience with CUDA and GPU processing techniques
Proficiency with hard example mining, active learning or dataset composition techniques
Preferred
Familiarity with common Perception, Planning and Foundation model concepts in Autonomous Driving
Experience deploying ML models to resource-constrained hardware
Experience with CUDA and GPU processing techniques
Proficiency with hard example mining, active learning or dataset composition techniques
Experience calculating metrics for and evaluating autonomous vehicle models