Tesla - Palo Alto, CA
posted about 1 month ago
Tesla is on a path to build humanoid robots at scale to automate repetitive and boring tasks. The goal of our reinforcement learning team is to build and demonstrate a general robot learning system that can leverage AI to perform complex physical tasks, ranging from full body locomotion, precise manipulation, and more. Our reinforcement and imitation learning engineers are responsible for end-to-end robotic learning and own this stack from inception to deployment. Most importantly, you will see your work repeatedly shipped to and utilized by thousands of humanoid robots in real world applications. As a Software Engineer specializing in Reinforcement Learning, you will develop end-to-end robotic learning systems using either reinforcement or imitation learning techniques. This involves reinforcing the correct set of actions, rewarding correct behavior, and negating incorrect behavior through real-time action/reward feedback loops. You will be tasked with performing a large number of instructions and generalizing new tasks with different objects and environments. Additionally, you will learn to perform dexterous tasks using high degree of freedom hands and develop different robot policies to solve language-conditioned tasks from vision. Your work will culminate in shipping production quality, safety-critical software that will be integral to the functionality of Tesla's humanoid robots.