ML Engineer Behavior Planning
Posted 2
views
Summary
Builds and deploys onboard behavior-planning models for Aurora's self-driving vehicles using imitation and reinforcement learning, plus critic and foundation models for driving evaluation and simulation. Day-to-day is large-scale ML training and production deployment on public-road vehicles, centered on Python, PyTorch, and distributed training.
You will design and deploy onboard planning models using imitation and reinforcement learning. You will build critic and foundation models for driving evaluation and simulation, advance autonomous-driving research, and deploy production models on public-road vehicles.
Responsibilities
- Develop and deploy large-scale onboard planning models
- Train models using imitation learning and reinforcement learning
- Develop offboard critic models for driving-behavior evaluation
- Architect foundation models for simulation
- Create world models for autonomous-driving edge cases
- Advance autonomous-driving technology from research to production
- Deploy models on production vehicles
Requirements
- BS, MS, or PhD in Robotics, Machine Learning, Computer Science, or a related quantitative field, or equivalent practical experience
- 2+ years of experience developing state-of-the-art ML models in research or production
- 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 for high-performance, maintainable code
- Experience with PyTorch or another modern ML framework
- Mastery of modern ML architectures including Transformers and Diffusion Models
Benefits
- Annual bonus
- Equity compensation
- Benefits