Perception Autonomy Engineer - Runtime Optimizations

Summary

Join May Mobility, a leading autonomous vehicle technology company, as a Senior Perception Engineer or above. In this critical role, you will enhance on-vehicle perception capabilities, ensuring robust performance for real-time applications. You will collaborate with cross-functional teams to define software and system requirements, integrate perception algorithms, optimize distributed training infrastructure, and conduct rigorous testing. The position requires expertise in perception systems, machine learning, and GPU optimization. You will develop and optimize perception stack software using CUDA and GPU programming, optimize machine learning models for various architectures, and stay at the forefront of relevant technologies. May Mobility offers a competitive salary and a comprehensive benefits package.

Requirements

• Strong programming skills in C++ and Python with a deep understanding of software optimization
• Extensive experience in optimizing ML models for resource-constrained inference, including custom operations, model pruning, quantization, and knowledge distillation
• Expertise in GPU programming, particularly CUDA, for high-performance computing and efficient parallel processing
• Proficiency in model-platform co-optimization, ensuring efficiency across GPU, TPU, and CPU architectures
• Hands-on experience with real-time data processing and advanced optimization techniques
• Strong background in ML model inference optimization, balancing accuracy and latency for real-time applications
• Familiarity with machine learning frameworks and libraries for perception-related tasks
• Excellent problem-solving skills with a detail-oriented approach and a rigorous testing mindset to ensure system reliability
• Master’s or PhD degree in Robotics, Computer Science, Computer Engineering, or a related field with strong mathematical and engineering foundations
• A minimum of 3+ years of GPU programing/optimization using CUDA or similar techniques for perception algorithms and models
• Proficiency in C/C++/Python and experience in software development in Linux environments
• Strong experience with GPU programming, CUDA, and real-time data processing
• Experience optimizing ML models for runtime efficiency
• Experience with 3D computer vision and point cloud processing

Responsibilities

• Work closely with across functional teams to co-define software and system requirements, analyze trade-offs, and shape the future generation of compute platforms
• Collaboratively integrate perception algorithms and machine learning models with vehicle hardware and software, ensuring seamless operation within autonomous driving systems
• Collaborate with ML infrastructure teams to develop and optimize distributed training infrastructure, automate deployment pipelines, and enhance system reliability and performance
• Conduct rigorous testing and validation of perception algorithms in both simulated and real-world environments to ensure robustness, reliability, and safety
• Develop and optimize perception stack software using CUDA and GPU programming to accelerate computationally intensive tasks and maximize efficiency
• Optimize machine learning models for runtime efficiency, scalability, and performance across GPU, TPU, and CPU architectures, ensuring adaptability to various vehicle platforms
• Stay at the forefront of machine learning, GPU programming, and autonomous driving technologies, integrating the latest advancements into the development process
• Actively participate in feature design, code reviews, debugging, and issue resolution, driving improvements in perception software performance

Preferred Qualifications

• Expertise in ML/DL model optimization for real-time applications with limited compute resources
• Strong contributions to deployed robotic systems, demonstrating field-proven capabilities in perception evaluation and testing
• Experience with robotics middleware such as ROS (Robot Operating System)
• Knowledge of vehicle dynamics and control systems
• Experience deploying ML models efficiently on embedded hardware
• Familiarity with hardware acceleration techniques beyond GPUs, such as TPUs and FPGAs

Benefits

• Comprehensive healthcare suite including medical, dental, vision, life, and disability plans
• Domestic partners who have been residing together at least one year are also eligible to participate!
• Health Savings and Flexible Spending Healthcare and Dependent Care Accounts available
• Rich retirement benefits, including an immediately vested employer safe harbor match
• Generous paid parental leave with immediate eligibility as well as a phased return to work
• Flexible vacation policy in addition to 18 paid company holidays
• Total Wellness Program providing numerous resources for overall wellbeing