Galamad Aerospace leverages technological advancements to produce capable and cost-efficient satellites.

Project Role: Reinforcement Learning Engineer (Autonomous Satellite Navigation)

As a Reinforcement Learning Engineer at our satellite company, you will spearhead the development of advanced algorithms and models to enable satellites to navigate autonomously and intelligently in space. You will leverage state-of-the-art reinforcement learning techniques to train satellites to perform complex tasks, such as pointing to ground stations, adjusting their orbits, and optimising their trajectories, all while maximising mission objectives and efficiency.

Trainee's responsibilities include but are not limited to:

• Using existing ML frameworks to implement reinforcement learning algorithms and architectures tailored to the unique challenges of autonomous satellite navigation.
• Develop physics-rich simulation environments (with Earth, moon, satellites, etc) using tools such as Unity to model satellite dynamics, orbital mechanics, and environmental factors.
• Utilise Python, C++, and other relevant programming languages to implement and optimise reinforcement learning models for real-time satellite control.
• Collaborate closely with satellite engineers to integrate learning-based navigation systems into satellite hardware and onboard software.
• Conduct extensive experimentation and evaluation to validate the performance, robustness, and safety of autonomous navigation algorithms in simulated and real-world environments.
• Stay abreast of the latest advancements in reinforcement learning, machine learning, and space technology to drive innovation and push the boundaries of autonomous satellite navigation.