Software Engineer, Behavior Planning ML… at Aurora · Pittsburgh

Summary: Aurora is dedicated to delivering self-driving technology safely and efficiently. They are seeking a Software Engineer to join their Behavior Planning ML Platform team, responsible for building and optimizing pipelines for model training and evaluation, as well as the infrastructure for deploying models onboard vehicles. Responsibilities: - Develop large scale pipelines for data extraction, model training and model evaluation - Build and optimize onboard ML infrastructure used to deploy models and run inference onboard the vehicle - Collaborate closely with motion planning, systems engineering, and other autonomy groups to define and develop critical ML workflow requirements Required Qualifications: - BS or higher degree in Computer Science/Engineering or related fields - > 6 months of experience - Strong programming skills in C++ or Python, ideally both - Experience with machine learning frameworks (PyTorch or TensorFlow) - Solid foundation in computer science fundamentals - especially operating system concepts including concurrency, memory management and process scheduling Preferred Qualifications: - Experience with GPU programming and Nvidia profiling tools - CUDA, NSight Systems, Nsight Compute - Experience working in cloud compute (AWS, Azure, GCP) ideally with batch processing or other large-scale workflow management platforms - Experience profiling and optimizing software on Linux Required Skills: C++, Python, Machine learning frameworks, PyTorch, TensorFlow, Operating system concepts, Concurrency, Memory management, Process scheduling Benefits: Annual bonus, Equity compensation, Benefits