Aurora's mission is to deliver the benefits of self-driving technology safely, quickly, and broadly. The Machine Learning Engineer, Synthetic Data will work with a world-class team to generate synthetic data to train and validate sensing models, helping to understand the world around the autonomous vehicle.
Requirements
- Excellent software engineering skills in Python
- Experience in Deep Learning (2+ years preferred).
- Experience in Computer Vision or generative Computer Graphics
- Experience with Pytorch/Tensorflow/Jax or similar frameworks
- Experience with synthetic training data.
- Previous experience with generative ML models, e.g. diffusion models,
Responsibilities
- Work on research, development, and deployment of state-of-the-art methods in computer graphics/vision and machine learning.
- Train sensing ML models on synthetic training data.
- Collaborate across various cross-team projects, providing ample opportunities for growth and impact on the Aurora Driver.
- Help unlock new sensing model capabilities using synthetic training data.
- Develop generative AI data generation pipelines.
- Surface high-impact findings to relevant Engineering leadership, keeping feedback loop going to influence Aurora’s synthetic data and ML strategy.
Other
- Bachelor’s degree in Computer Science or a related field.
- Strong critical thinking, collaboration, and communication skills.
- Master’s or PhD in Computer Science.
- Top-tier publications in related fields (e.g., CVPR, ECCV, ICCV, IJCV, ICML, NeurIPS, JMLR, PAMI, SIGGRAPH, TOG)
