Opportunity to work on a new solution from scratch in a technical complex environment
Work in an international, agile, cross-functional team creating the future of autonomous systems
Grow your career in a expanding and ambitious engineering team
Build innovative products using state-of-the-art technologies in AI, robotics, and autonomy
Benefit from a steep learning curve and continuous development
Enjoy team events and a strong, collaborative culture

Build real autonomous systems that operate in the real world, not in the lab.

Join our engineering team of a new product and help build the core autonomy that powers our next generation robotic systems used for defense and mission-critical operations. You will design, implement, and harden robotic software that must perform under real operational conditions - outdoors, under uncertainty, with real consequences. Your work will directly shape the reliability, safety, and tactical capability of the systems we deliver.

Research and prototype novel RL algorithms (e.g. exploration, POMDPs, multi-agent systems)
Define, design and implement use-cases for DRL on edge devices
Translate theory into scalable systems with support from our engineering teams
Collaborate with simulation, autonomy and AI infrastructure teams
Develop decision-making for intelligent behavior and architectures

Deep knowledge of RL theory and practice: policy gradients, value iteration, Q-learning, etc.
Experience with ML training in physics based simulation (Gazebo, IsaacSim, Mujoco, Carla, etc.).
Strong Programming proficiency (Python, C/C++).
Comfortable with ML tooling and maintaining ML pipelines (Pytorch Lightning, MlFlow, etc.).
Have experience with deploying ML methods to physical devices.
Experience with version control (git).
Familiarity with statistics, evaluation methods and experiment design.
You think rigorously and build practically.

PhD in Reinforcement Learning, Robot Engineering or equivalent with experience in deploying developed methods to real robots.
OR masters degree in relevant field with extensive experience in RL.
Experience with sensor based end-to-end ML architectures.
Familiar with Transformers, Attention, Graphs, VLAs and other modern day ML building blocks.
Publications at NeurIPS, ICLR, ICML, ICRA, IROS, etc. are a plus
Experience with robotics middleware (ISAAC, ROS/ROS2, etc.)

Willingness to travel
Citizenship of NATO member country or closed allied are mandatory

Reinforcement Learning Research Engineer – Exploration & Decision Intelligence (m/w/d)