Applied Scientist - Learning-Based Navigation and Locomotion

Robotics and AI Institute; Zürich; On-site; CHF 120,000 - 180,000; Full time

Job summary

Robotics and AI Institute in Zürich invites a committed Applied Scientist to advance reinforcement learning for mobile robots. You will develop end-to-end control from sensor data and translate research into deployable systems.

The role requires hands-on ML and robotics experience, strong coding skills in Python or C++, and collaboration with hardware teams to validate algorithms on real hardware.

Qualifications

• MS/PhD or equivalent in robotics, CS, or related fields.
• 2+ years of research and development experience.
• Proficiency in Reinforcement Learning, Control, Robotics, or Imitation Learning.
• Experience with sim-to-real for legged robots or highly dynamic mobile vehicles.
• Experience in perception-based control.
• Advanced programming in Python or C++.
• Experience with PyTorch and robotic simulation.

Responsibilities

• Develop RL-based navigation or locomotion methods from sensor data.
• Work on end-to-end control for mobile robots in simulation and real hardware.
• Collaborate with hardware teams to validate models on legged robots.

Skills

Reinforcement Learning

Python or C++

Deep learning (PyTorch)

Robotics perception

Sim-to-real for legged robots

RL/Control/Imitation Learning

Education

MS/PhD in robotics or CS

Tools

ROS/ROS2

Docker

Robotic simulation

Job description

Our Mission

Our mission is to solve the most important and fundamental challenges in AI and Robotics to enable future generations of intelligent machines that will help us all live better lives.

We aim to advance the mobility and autonomy of mobile robots to new heights by leveraging simulation based methods like Reinforcement Learning, augmenting them with model information.

Reinforcement Learning Applied Scientist will have proven hands-on research or industry experience focusing on one or more of these key areas: Learning-based navigation or locomotion, specifically end-to-end control methods from sensor data. Having practical hardware experience is essential for this role. If you are passionate about developing technology for robots and using it to advance their capabilities and usefulness, this team will be a great fit for you!

What you'll need

• MS/PhD or equivalent industry experience in robotics, computer science, or related fields
• 2+ years of experience in research and development
• Ability to demonstrate technical proficiency in Reinforcement Learning, Control, Robotics, or Imitation Learning
• Experience with sim-to-real for robotic hardware specifically legged robots or highly dynamic mobile vehicles.
• Experience in working with perception-based control
• Advanced programming skills in Python or C++
• Expertise with deep learning frameworks such as PyTorch and robotic simulation

Bonus

Experience in any of the following is a plus; none is required.

• Knowledge of Model Predictive Control
• Knowledge in robot perception
• Experience in combining model-based and data-driven approaches
• Experience in working with Isaac-Lab
• Experience in working with ROS or ROS2
• Experience with Docker, cloud computing, or similar applications
• Experience with parallel programming (e.g., CUDA)
• Proven track record in top-tier conferences and journals in Machine Learning, Robotics, Control, or related fields
• These attributes are great to have but not required. Candidates who lack these should not be discouraged from applying.

We provide equal employment opportunities to all employees and applicants for employment and prohibit discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.