Research Engineer, Robotics RL & Post-Training

On-site · Munich (Germany) · Mid · Full-time

Want offers like this one?

Create your free PyHires profile: you will see how well you match each offer and get a weekly email with the ones that fit you.

Create my profile

Overview

Work mode
On-site
Location
Munich (Germany)
Engagement
Full-time
Seniority
Mid
Languages
English
Open to candidates from
EU countries only
Company
microagi
Posted
Nov 19, 2026

About the role

microagi captures manual work in Europe's industrial champions, trains foundation models on it and deploys robots onto the factory floor. As a Research Engineer for robotics RL and post-training in Munich, you will train policies for contact-rich manipulation and take them from research implementation to real-robot evaluation. What you'll do - Train and refine RL policies for contact-rich manipulation: precise assembly, insertion and recovery from failures - Develop rewards, curricula and reset strategies for efficient policy learning - Distil specialist capabilities into generalist policies with expert data, imitation learning and teacher-student methods - Investigate direct RL post-training of vision-language-action models - Evaluate policies on real robots What you bring - Strong Python and PyTorch or JAX, owning work from research implementation to real-robot evaluation - Experience with sim-to-real transfer and a robotics simulation stack such as MuJoCo or Isaac Sim / Isaac Lab - Substantial research contributions (CoRL, RSS, ICRA, IROS, NeurIPS, ICML or ICLR) or equivalent work - Intensity, an entrepreneurial attitude and a wish to work in person in the office What they offer - Base salary plus equity - An early seat in one of Europe's fastest-growing deep-tech companies - Free food and drinks in the office, and a reply to every application within five working days

Requirements

Based on:Python

Must-have

  • JAX
  • PyTorch

About microagi

microagi is a data research and deployment lab for embodied AI: its Atlas platform captures manual work inside Europe's industrial champions, trains foundation models on it and deploys robots onto the floor. Founded by former Formula 1 engineers and a researcher from the Alan Turing Institute, it raised a USD 55M seed round and is based in Munich, with a research centre in Zurich and teams in London, New York and Istanbul.

Stack

  • Python
  • JAX
  • PyTorch

Company

microagi logo
microagi
Germany
View company profile