Machine Learning Engineer II - Autonomous Driving & Inference Runtime
Role details
Job location
Tech stack
Job description
May Mobility is entering an exciting phase of growth as we expand our first-of-its-kind autonomous shuttle and mobility services across the nation. Launched in 2017 with a strong team of experienced roboticists and software engineers with decades of experience fielding robotic systems in the wild, May Mobility is looking to expand its team of robotics engineers with a background in robotics or autonomous vehicles., * 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., * Architecting software for low-level GPU/CPU concurrency such as CUDA streams, pinned memory, kernel fusion and memory-layout optimization.
- Use of compilation and runtime utilities such as TensorRT, ONNX and torch.compile for edge deployments.
- Apply quantization, distillation, and pruning to fit models within onboard compute and memory budgets.
Requirements
Do you have experience in Software engineering?, Do you have a Master's degree?, We are seeking ML-Oriented Software Engineers with experience in robotics applications. As part of our Autonomous Driving ML team, you will use your knowledge of Software and Hardware concepts to deploy, optimize and scale State of the Art Machine Learning models for both Datacenter and Edge Vehicle devices., * 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.
Desirable
- 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).
Benefits & conditions
3.43.4 out of 5 stars Remote $180,000 - $210,000 a year, Pulled from the full job description
- Paid parental leave
- Parental leave
- Health insurance
- Retirement plan
- Vision insurance
- Dental insurance
- Flexible spending account, + Prolonged sitting
- Prolonged standing
- Prolonged computer use
Travel required? - Low 5-10%
Benefits and Perks
- 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 as well as a phased return to work.
- Flexible vacation policy in addition to paid company holidays.
- Total Wellness Program providing numerous resources for overall wellbeing