RL Engineer — Robotics, Zurich, Stock Options

Baseline Robotics; Zürich; On-site; CHF 120,000 - 145,000; Full time

Benefits offered by this job

Stock options

Job summary

Baseline Robotics in Zurich, Switzerland, on-site 5 days a week, is seeking an AI scientist to advance reinforcement learning for robotic control and policy improvement on our shared hardware platform.

You will work on post-training policy improvements, safety-focused exploration, and developing reward models from vision, language, and operator feedback. A strong RL background in robotics, simulations, or games and publications or equivalent experience are highly valued.

Qualifications

• Experience training reinforcement-learning systems in robotics, simulation, games, or agents.
• Knowledge of modern policy-gradient and value-based reinforcement learning methods.
• Publications in top machine learning or robotics venues, or equivalent experience.

Responsibilities

• Improve policies on the robots with post-training and reinforcement learning.
• Design reward models from vision, language, and operator feedback.
• Stop or recover trials with safety constraints before the hardware is damaged.

Skills

RL in robotics

Policy gradients

Publications in ML/Robotics

Job description

Baseline Robotics in Zurich, Switzerland, on-site 5 days a week, is seeking an AI scientist to advance reinforcement learning for robotic control and policy improvement on our shared hardware platform.

You will work on post-training policy improvements, safety-focused exploration, and developing reward models from vision, language, and operator feedback. A strong RL background in robotics, simulations, or games and publications or equivalent experience are highly valued.