Behavior & Planning Intern — ML for Self-Driving

Auror Limited; Mountain View (CA); On-site; USD 72,000 - 90,000; Full time

Job summary

Aurora is seeking Summer 2027 Behavior & Planning Interns to work on how the driver decides what to do, including forecasting and trajectory planning using ML and optimization.

You will develop end-to-end planning or prediction models, reason about uncertainty, and work with large-scale datasets under mentorship. This paid internship offers in-person collaboration in Mountain View/San Francisco and potential for growth.

Qualifications

• Pursuing a Bachelor’s, Master’s or PhD in Computer Science, Robotics or related field with ML focus.
• Hands-on ML with PyTorch: dataloaders, architectures, losses.
• Exposure to imitation learning or RL or motion planning.
• Experience training models on large-scale datasets or benchmarks.
• Ability to reason mathematically about optimization objectives.
• Awareness of distribution shift in imitation learning.

Responsibilities

• Develop end-to-end planning or prediction models for the Aurora Driver using imitation learning, RL, and/or classical motion planning.
• Formulate ambiguous driving-behavior problems as concrete ML or optimization problems.
• Reason about progress vs. safety and uncertainty in model design and evaluation.
• Work with autonomy/robotics-scale datasets and benchmarks, not toy datasets.
• Present a project plan and regular progress updates to the team with mentor guidance.

Skills

ML foundations

PyTorch experience

Imitation learning

Reinforcement learning

Optimization theory

Dataset handling

Education

Pursuing CS/Robotics degree (ML focus)

Tools

PyTorch

Job description

Aurora is seeking Summer 2027 Behavior & Planning Interns to work on how the driver decides what to do, including forecasting and trajectory planning using ML and optimization.

You will develop end-to-end planning or prediction models, reason about uncertainty, and work with large-scale datasets under mentorship. This paid internship offers in-person collaboration in Mountain View/San Francisco and potential for growth.