Staff/Lead Machine Learning Engineer, Behavior & Planning

About the role

Nuro is a physical AI company developing Level 4 autonomous driving technology for a wide range of vehicles, use cases, and markets. The company believes self-driving vehicles are the most immediate and profound opportunity for AI to drive positive change in the physical world. This role is a Staff Machine Learning Engineer position on the Behavior & Planning team, where the hire will serve as a technical leader responsible for how the Nuro Driver behaves on the road. The position requires setting technical direction and leading initiatives that span multiple teams with a high degree of autonomy. You will work at the frontier of applied machine learning, turning large-scale driving data into safe and natural driving behavior. The role offers a clear path to grow into a management or tech-lead position as the team scales. If you love solving hard new problems and seeing your models drive real robots in the physical world, this is the opportunity for you.

Key facts

What you'll do

Define technical strategy and frame ambiguous problems for the Behavior and Planning stack, driving initiatives from idea to on-road deployment with minimal oversight.

Design, train, and productionize state-of-the-art models spanning foundation and world models, LLM/VLM reasoning, reinforcement and imitation learning, generative and diffusion models, and transformer-based prediction and planning.

Build behavior and planning models that generalize to new cities and geographies across the U.S. and globally, and adapt to new vehicle platforms including robotaxi, personally owned vehicles, and delivery or logistics fleets.

Partner closely with Perception, Simulation & Evaluation, and ML Infra teams, as well as the broader Autonomy and Research organizations, to develop holistic solutions to top autonomy challenges.

Own the full model lifecycle, including data strategy, training pipelines, onboard inference, closed-loop and open-loop evaluation, and continuous on-road iteration.

Raise the technical bar of the team by mentoring engineers and researchers, and shaping roadmap and technical strategy beyond your immediate scope.

Translate large-scale driving data into safe, comfortable, and natural driving behavior that meets real-world performance requirements.

Evaluate and benchmark models rigorously to ensure safety, robustness, and generalization across diverse driving scenarios and edge cases.

Collaborate with cross-functional stakeholders to align on priorities and unblock shared initiatives that impact autonomy performance.

Contribute to the development of industry-leading methodologies for world modeling, prediction, and planning in autonomous systems.

Requirements

7+ years building and deploying machine learning systems, with a track record of leading complex, multi-team technical initiatives.

M.S. or Ph.D. in Computer Science, Artificial Intelligence, Machine Learning, Robotics, or a related field or equivalent practical experience.

Strong, general machine learning foundations with the ability to reason from first principles across model architectures, training, and evaluation.

Experience applying machine learning to real-world physical systems, with a proven track record of deploying models in production environments.

Deep understanding of transformer-based architectures, world models, and their application to perception, prediction, and planning.

Proficiency with large-scale data pipelines and the ability to design data strategies that improve model performance and generalization.

Experience with simulation and evaluation frameworks, including closed-loop testing and metrics-driven decision making.

Strong written and verbal communication skills to articulate technical trade-offs and lead cross-functional discussions.

Nice to have

Experience with reinforcement learning and imitation learning for autonomous driving applications.

Background in robotics or physical AI systems that interface with the real world.

Knowledge of logistics or delivery vehicle platforms and their operational constraints.

Experience contributing to open-source machine learning frameworks or tooling.

Practical notes

This is a full-time position based in Mountain View, California.

The role requires on-site presence at the headquarters.

Eligibility to work in the United States without sponsorship is required.

Candidates must meet the stated experience and educational requirements as hard bars.