Tesla

Makes electric cars, robotaxis and grid batteries

Applied Reinforcement Learning Engineer - Whole Body Controls, Optimus

Robotics & Autonomous SystemsUpdated on Nov 11

Full-timePalo Alto, CA, USANo salary listedIn-person

About the Job

Requirements

Proficiency in Python, including NumPy and PyTorch.
Solid understanding of robotics fundamentals, including geometry, linear algebra, kinematics, dynamics, probability, and statistics.
A controls or robotics background, with hands-on experience applying reinforcement learning to control problems.
Experience working with robotic systems; experience with legged robotic systems with high degrees of freedom is ideal.
Experience with sim-to-real techniques or a good understanding of physics fundamentals.
Equivalent experience through projects, research, or coursework is acceptable.

Responsibilities

Develop end-to-end reinforcement-learning policies for whole-body movements spanning locomotion and manipulation.
Design observations, actions, and rewards based on physics first principles.
Develop techniques to improve sim-to-real transfer, including classical modeling, domain randomization, and learned dynamics models.
Define metrics that quantify controller performance, and evaluate policies in simulation and on hardware.
Ship production-quality policies to a fleet of robots.

Desired Qualifications

Familiarity with state estimation and proprioceptive sensing, such as IMU.
Experience with C++ and production or real-time software.
Hands-on experience deploying and running controllers on real robot hardware.
Experience with massively parallel simulation, such as mjlab or IsaacLab.

Category	Tesla SI
Location	Palo Alto, California
Requisition ID	276000
Type	Full-time

Job Description

<div class="MSWordContent"><p>Tesla SI is solving robust embodied intelligence through humanoid robots. On the Whole Body Controls team, you will develop the policies and controllers that let Optimus walk, dance, balance, recover from disturbances, and manipulate objects in real-world settings — the layer of the motion stack that turns high-level intent into physically robust motion on real hardware. 

This role is for engineers who come from a controls or robotics background and have applied reinforcement learning to control problems. Most importantly, the motion policies you deploy will be repeatedly shipped to and used by thousands of humanoid robots in real-world applications. We hire at all levels, including recent graduates with strong controls or robotics fundamentals and a demonstrated project or research record.</div>

Job Responsibilities

Develop end-to-end reinforcement-learning policies for whole-body movements, spanning locomotion and manipulation
Design observations, actions, and rewards based on physics first principles
Develop techniques to improve sim2real transfer, including classical modeling, domain randomization, and learned dynamics models
Define the metrics that quantify controller performance, and evaluate policies both in simulation and on hardware
Ship production-quality policies to a fleet of bots

Job Requirements

Proficiency in Python (numpy, pytorch)
Solid understanding of robotics fundamentals, including geometry, linear algebra, kinematics, dynamics, probability, and statistics
A controls or robotics background, with hands-on experience applying reinforcement learning to control problems
Experience working with robotic systems, ideally legged robotic systems with high degrees of freedom
Experience with sim2real techniques or a good understanding of physics fundamentals
Familiarity with state estimation and proprioceptive sensing (e.g. IMU) is a plus
Experience with C++ and production / real-time software is a plus
Preferred: hands-on experience deploying and running controllers on real robot hardware; experience with massively parallel simulation (e.g. mjlab, IsaacLab)
Equivalent experience through projects, research, or coursework is acceptable

About the Company

Tesla

Makes electric cars, robotaxis and grid batteries

Tesla makes electric cars and batteries that store power for homes and utilities, and it develops self-driving software and humanoid robots. In 2023, its Model Y became the first electric vehicle to rank as the world's best-selling car. Buyers order the Model 3 sedan, Model Y SUV, or Cybertruck pickup directly from Tesla instead of through dealers, and they charge on its Supercharger fast-charging network. It also sells Megapack and Powerwall batteries, runs a robotaxi service, and charges drivers a monthly fee for self-driving software that still needs their supervision. Tesla was founded in 2003, with Elon Musk as its lead early investor and a recognized co-founder, and it is based in Austin, Texas.

Company size: 10,001+
Company stage: IPO
Headquarters: Austin, TX
Founded: 2003

Recently Posted Jobs

Explore more opportunities at Tesla

See more jobs