The Offline Driving Intelligence team at Zoox is looking to develop Foundation Models for ML Agents and planning, applying them off-vehicle to provide generalization capabilities to simulation and validation, in order to improve driving performance in autonomous vehicles.
Requirements
- Experience in Planning and / or Prediction using Reinforcement Learning techniques
- Experience with training and deploying transformer-based model architectures
- Experience with production Machine Learning pipelines: dataset creation, training frameworks, metrics pipelines
- Fluency in Python with a basic understanding of C++
Responsibilities
- You will develop new deep learning models that use imitation learning and reinforcement learning to generate driving plans for human-like agents.
- You will work on novel techniques to estimate the quality of those driving plans along the dimensions of safety, progress, comfort and realism.
- You will contribute to 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, Simulation, and Validation to solve the overall Autonomous Driving problem.
Other
- PhD degree in computer science or related field +1y of professional experience (top tier publications can remove the need for the year of experience) or, MSc +5y of professional experience in a relevant field.
- Bonus Qualifications: Top tier publications (NeurIPS, ICML, CVPR)
