Reinforcement Learning Engineer, Self-driving

Tesla Tesla · Auto · Palo Alto, CA · Tesla AI

This role focuses on building foundation models for robotics using reinforcement learning, generative modeling, and imitation learning to create an end-to-end self-driving system. The engineer will leverage large-scale driving data and integrate directly with vehicle firmware to ship safety-critical software to millions of customers.

What you'd actually do

  1. Leverage millions of miles of driving data and interventions to build a robust and scalable end-to-end learning based self-driving system
  2. Use cutting-edge techniques from generative modeling, imitation learning, and reinforcement learning to improve the planning and reasoning capabilities of our driving models
  3. Experiment with data generation and fleet data collection approaches to enhance the diversity and quality of training data
  4. Integrate directly with vehicle firmware and ship production quality, safety-critical software to the entirety of Tesla's vehicle fleet

Skills

Required

  • Python
  • deep learning framework
  • software engineering best practices
  • deep learning modern architectures
  • optimization
  • model alignment
  • deploying production ML models
  • C++
  • reinforcement learning
  • generative modeling
  • imitation learning

Nice to have

  • planning and reasoning capabilities

What the JD emphasized

  • safety-critical software
  • production ML models
  • self-driving
  • robotics

Other signals

  • end-to-end learning based self-driving system
  • generative modeling, imitation learning, and reinforcement learning
  • ship production quality, safety-critical software to the entirety of Tesla's vehicle fleet
  • deploying production ML models for self-driving, robotics, or natural language processing at scale