Autonomous Driving: ML Engineer, Behavior Planning

Aurora Innovation Inc.; Mountain View (CA); On-site; USD 139,000 - 223,000; Full time

Benefits offered by this job

Annual bonus

Equity compensation

Benefits

Job summary

Aurora Innovation Inc. seeks a ML Engineer on the Behavior Planning Team to advance autonomous driving with large-scale Imitation and Reinforcement Learning. You will design onboard planning architectures and offboard evaluation systems that push safety and efficiency in real-world driving.

You will also build simulation engines, world models, and deploy models to production vehicles, collaborating with a team of researchers and engineers to meet the highest safety standards.

Qualifications

• BS, MS, or PhD in Robotics, Machine Learning, Computer Science, or related field, or equivalent practical experience.
• 2+ years of experience developing state-of-the-art ML models, either in a research or production setting.
• Hands-on experience with Imitation Learning or Reinforcement Learning for physical or simulated agents.
• Experience training large models on massive datasets using distributed computing.
• Fluency in Python with high-performance, maintainable code.
• Deep experience with PyTorch (preferred) or other ML frameworks; mastery of Transformers and Diffusion Models.
• Publications in top ML conferences (NeurIPS, ICML, CoRL, CVPR, AAAI).
• Experience deploying complex ML systems in production.

Responsibilities

• Define the architecture of onboard planning models using large-scale Imitation Learning and Reinforcement Learning.
• Develop and deploy models enabling the Aurora Driver to navigate complex environments safely.
• Create offboard critic models to evaluate driving behavior at scale for improved comfort, progress, and safety.
• Architect offboard foundation models for a realistic world model to test the driver against many edge cases.
• Bridge research and production by deploying models on real vehicles meeting safety standards.

Skills

Python

PyTorch

C++

Imitation Learning

Reinforcement Learning

Distributed computing

Transformers

Education

BS/MS/PhD in Robotics/ML/CS

Tools

PyTorch

Transformers

Diffusion Models

C++

Job description

Aurora Innovation Inc. seeks a ML Engineer on the Behavior Planning Team to advance autonomous driving with large-scale Imitation and Reinforcement Learning. You will design onboard planning architectures and offboard evaluation systems that push safety and efficiency in real-world driving.

You will also build simulation engines, world models, and deploy models to production vehicles, collaborating with a team of researchers and engineers to meet the highest safety standards.