Machine Learning Engineer II - Autonomous Driving & Inference Runtime

May Mobility is transforming cities through autonomous technology to create a safer, greener, more accessible world. They are seeking ML-Oriented Software Engineers with experience in robotics applications to deploy, optimize and scale Machine Learning models for Autonomous Driving. The role involves working with both Datacenter and Edge Vehicle devices.

Responsibilities:

• Deploy and Optimize Machine Learning model architectures across May’s Autonomous Driving training and inference stacks
• Own the model-compilation and deployment pipeline end-to-end
• Establish and defend latency/throughput budgets across the AV stack, including profiling, regression and integrity tests

Requirements:

• Bachelor's or Master's degree in Robotics, Computer Science, Computer Engineering, or a related field with strong mathematical and engineering foundations
• A minimum of 2 years writing software to interface with GPU and ML systems
• Proficiency in C/C++/CUDA/PyTorch and experience in Linux environments
• Familiarity with basic Perception and Planning concepts in Autonomous Driving
• Familiarity with NVIDIA compute architectures (Ada, Hopper, Blackwell, etc)
• Familiarity with common profiling tools such as Nsight, Pytorch Profiler, flamegraph
• Understanding of Quantization (INT8/FP8/FP16) and other compression techniques
• Familiarity with NVIDIA DRIVEOS architecture and SoCs (Orin/Thor)
• Familiarity with techniques for scaling training throughput (batching, FSDP, streaming dataloaders)