Skip to main content

Zoox

Machine Learning Engineer - ML Agents and Planning

Foster City, CA$189k–$270kfull-timemidAdded yesterday

About this role

Join the Offline Driving Intelligence team to develop foundation models for ML agents and planning systems that enable autonomous vehicle simulation and validation. You'll create cutting-edge machine learning pipelines to predict agent behavior and optimize vehicle planning decisions.

What you'll do

  • Design and implement machine learning pipelines for agent behavior prediction and vehicle planning
  • Develop foundation models applicable to simulation and validation environments
  • Collaborate with planner, simulation, and validation teams to validate driving performance
  • Build models that generalize across off-vehicle scenarios
  • Optimize course-of-action planning for autonomous vehicles
  • Contribute to novel ML approaches for multi-agent prediction

What they're looking for

  • Machine learning model development and training
  • Python or C++ programming
  • Deep learning frameworks (PyTorch, TensorFlow, or similar)
  • Multi-agent simulation and planning
  • Data pipeline construction and optimization
  • Autonomous vehicle domain knowledge
  • Software engineering best practices
  • Collaboration with cross-functional teams
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Zoox

Zoox develops autonomous vehicle technology and robotaxi systems, supported by manufacturing operations and AI validation infrastructure. The company is hiring for part-time student roles in hardware-software integration, manufacturing software engineering, AI testing and evaluation, and QA automation, as well as experienced engineers for simulation and AI performance assessment.

Website
zoox.com
View all jobs at Zoox

Likely interview questions

  • Describe your experience developing machine learning models for prediction tasks and how you've validated their generalization capabilities.
  • What approaches have you used to model multi-agent interactions, and how did you handle the complexity of competing objectives?