Machine Learning Software Engineer, Strategy Planning
Aurora Innovation
·
Posted:
May 2, 2023
·
Other
About the position
Aurora is seeking a Machine Learning Software Engineer for their Motion Planning Strategy Team. The successful candidate will be responsible for building machine learning approaches for motion planning, developing policies and plans to manage multi-actor interactions and plans under uncertainty, and developing approaches that interleave motion planning with forecasting of other agents. They will also be responsible for developing and implementing scalable production-grade algorithms for the Aurora Driver and leading the design and development of architectural components of the decision-making system of Aurora. The ideal candidate will have a BS, MS, or PhD in Robotics, Machine Learning, Applied Mathematics, Computer Science, or a related field, and 5+ years of strong programming and software design skills, ideally in C++ and/or Python. They should also have expertise with modern ML and GPU toolkits such as PyTorch, TensorFlow, JAX, TensorRT, and/or CUDA, and expertise with deployment of production ML models for self-driving, computer vision, or natural language processing at scale.
Responsibilities
- Build machine learning approaches for motion planning for creating, generating, and selecting comfortable and safe trajectories for a self-driving vehicle
- Develop policies and plans to manage multi-actor interactions and plans under uncertainty
- Develop approaches that interleave motion planning with forecasting of other agents
- Develop and implement scalable production-grade algorithms for the Aurora Driver
- Lead design and development of architectural components of the decision making system of Aurora
Requirements
- Build machine learning approaches for motion planning for creating, generating, and selecting comfortable and safe trajectories for a self-driving vehicle
- Develop policies and plans to manage multi-actor interactions and plans under uncertainty
- Develop approaches that interleave motion planning with forecasting of other agents
- Develop and implement scalable production-grade algorithms for the Aurora Driver
- Lead design and development of architectural components of the decision making system of Aurora
- BS, MS, or PhD in Robotics, Machine Learning, Applied Mathematics, Computer Science or related field
- 5+ years of strong programming and software design skills ideally in C++ and/or Python
- Knowledge of classical and modern ML approaches such as linear models, recurrent models, convolutional neural networks, transformer networks
- Expertise with modern ML and GPU toolkits such as PyTorch, TensorFlow, JAX, TensorRT, and/or CUDA
- Expertise with deployment of production ML models for self driving, computer vision, or natural language processing at scale
- Experience with imitation and reinforcement learning (desirable)
- Experience in designing, building, and productionizing motion planning algorithms, state estimation algorithms, probabilistic modeling, or statistical techniques (desirable)