Jobless Developer
Zoox logo
Zoox

Posted 19 months ago

Open

Software Engineer - Learned Trajectory Machine Learning Engineer

Foster City, CAOn-siteFull-time

AI Summary

Develops deep learning models and pipelines to generate driving trajectories for autonomous vehicles, using imitation and reinforcement learning, and evaluates plan quality across safety, progress, and comfort.

About this role

The Prediction & Behavior ML team is responsible for developing machine learning (ML) algorithms that learn and predict behaviors from data, applying them both on-vehicle to influence driving behavior and off-vehicle to provide ML capabilities to simulation and validation. Given the tight integration of behavior forecasting and motion planning, our team collaborates closely with the Planner team to advance overall vehicle behavior. We also work closely with our Perception, Simulation, and Systems Engineering teams to accelerate our ability to validate our driving performance.
As a Learned Trajectory Machine Learning Engineer you will be responsible for developing deep learned models that produce trajectories for our vehicles to drive. Given the tight integration of behavior prediction and motion planning, you will closely collaborate with the Planner and Perception teams in the advancement of our overall vehicle behavior.

In this role, you will:

  • You will develop new deep learning models that use imitation learning and reinforcement learning to generate driving plans for our autonomous vehicle. You will also work on techniques to estimate the quality of those driving plans along the dimensions of safety, progress, comfort etc.
  • You will leverage our large-scale machine learning infrastructure to discover new solutions and push the boundaries of the field
  • You will develop metrics and tools to analyze errors and understand improvements of our systems
  • You will collaborate with engineers on Perception, Planning, and Simulation to solve the overall Autonomous Driving problem in complex urban environments

    • Qualifications

  • BS, MS, or PhD degree in computer science or related field
  • Experience with training and deploying transformer-based model architectures and reinforcement learning
  • Experience with production Machine Learning pipelines: dataset creation, training frameworks, metrics pipelines
  • Fluency in C++ or Fluency in Python with a basic understanding of C++
  • Extensive experience with programming and algorithm design
  • Strong mathematics skills

    • Bonus Qualifications

  • Conference or Journal publications in Machine Learning or Robotics related venues
  • Prior experience with Prediction and/or autonomous vehicles or robotics in general

    • Skills

    Algorithm DesignAutonomous SystemsC++Dataset CreationImitation LearningLinear AlgebraMachine Learning PipelinesMetrics PipelinesProbabilityPublication ExperiencePythonReinforcement LearningRoboticsTraining FrameworksTransformer

    Explore related jobs

    More jobs at Zoox

    Similar Algorithm Design jobs

    Browse these categories

    Remote JobsC++ JobsPython JobsJobs in United States