Waymo is looking to improve the Waymo Driver's ability to navigate complex real-world scenarios by exploring state-of-the-art fine-tuning techniques such as reinforcement learning, LoRA base finetuning, and contrastive learning to learn from suboptimal driving data.
Requirements
- Experience with deep learning concepts and reinforcement learning and reward functions
- Proficient in Python and deep learning frameworks
- Proficiency in dealing with large amount of data
- Experience in the autonomous driving domain, including areas like motion planning, perception, or control
- Experience in integrating ML models into complicated systems
- Proficient in C++
- Proficient in PyTorch, JAX, or TensorFlow
Responsibilities
- Frame the open-ended real-world problems into well-defined ML problems; apply deep learning, reinforcement learning, imitation learning to these problems.
- Develop novel ways to learn from unsupervised driving data.
- Be able to apply SOTA techniques within Waymo's tooling/infrastructure.
- Build data tooling/infrastruction to unblock experimentation.
- Use data-driven decision making to evaluate and compare different approaches
- Collaborate closely with partner teams such as perception, research, simulation, and evaluation
Other
- Currently pursuing a Masters / PhD degree in Computer Science, Machine Learning, Robotics, or related field
- This will be a hybrid onsite internship position.
- To be in consideration for multiple roles, you will need to apply to each one individually - please apply to the top 3 roles you are interested in.
