Description
Shield Space is seeking a skilled and driven Principal Distributed Autonomy Engineer to join our founding technical team developing the UK’s next generation of autonomous space systems for orbital defence.
You will play a key role in building the software that enables satellites to cooperate, coordinate, and fight together in orbit. In the near term, you will contribute directly to the design and validation of single-agent reinforcement learning (RL) guidance and decision models. Over time, you will lead the development of the distributed autonomy framework that allows multiple spacecraft to operate as intelligent, self-organising swarms in contested environments.
This is a hands-on software development role working closely with the CTO and Principal Autonomy Engineer to design, train, and test advanced multi-agent guidance and coordination algorithms across simulation, hardware-in-the-loop, and on-orbit environments. The position blends deep technical implementation with systems-level design, bringing machine vision, guidance and control, and multi-agent collaboration into one coherent product system.
Having recently secured its first major investment, Shield Space is expanding its team to deliver nationally strategic missions and international collaborations. With our first orbital launch scheduled in just under 18 months, this position offers the chance to join the company at a formative stage, shaping the products, behaviours, and architectures that will underpin the UK’s first sovereign swarm autonomy capability. You will see your work influence real missions, collaborate with international partners, and help define how autonomous systems will operate and defend critical national infrastructure in orbit.
Responsibilities
* Design and implement reinforcement learning and control algorithms for spacecraft guidance and decision-making.
* Develop scalable multi-agent autonomy frameworks for coordinated behaviour, task allocation, and distributed guidance.
* Train and validate autonomous models within simulation and hardware-in-the-loop environments.
* Collaborate with the autonomy and systems teams to integrate perception, guidance, and coordination layers into a unified autonomy stack.
* Prototype communication and coordination protocols for low-latency, degraded-link cooperation between multiple spacecraft.
* Develop simulation campaigns to test collective behaviour, decision logic, and emergent swarm performance.
* Contribute to the verification and validation of autonomy subsystems, ensuring safe and explainable multi-agent behaviour.
* Produce clear, well-structured documentation, including interface definitions, validation reports, and design papers.
* Participate in technical reviews and provide mentorship within the autonomy development team.
* Support mission demonstration planning and contribute to strategic technical roadmaps for distributed autonomy development.
Essential Skills
* Proven experience developing multi-agent guidance, coordination, or control systems, ideally for autonomous spacecraft, UAVs, or robotic platforms.
* Strong understanding of multi-agent reinforcement learning (MARL) or distributed autonomy frameworks, including cooperative decision-making and task-allocation algorithms.
* Master's or PhD Degree in Computer Science, Aerospace Engineering, Robotics, or a closely related field.
* Proficiency in Python and C++, with hands-on experience implementing learning-based or control algorithms for autonomous vehicles.
* Hands-on experience with PyTorch, TensorFlow, or equivalent ML frameworks.
* Experience designing, testing, and validating autonomy software within high-fidelity or hardware-in-the-loop simulation environments.
* Solid mathematical foundation in optimisation, estimation, or control theory.
* Excellent problem-solving and communication skills, with the ability to work effectively within a small, multidisciplinary technical team.
Desirable Skills
* Understanding of spacecraft guidance, navigation, and control fundamentals.
* Knowledge of distributed communications or networked control relevant to multi-agent coordination.
* Experience with policy training, reward shaping, or safe-RL approaches for critical systems.
* Background in flight software, embedded systems, or real-time simulation integration.
* Prior involvement in startup or early-stage R&D environments.
Benefits
* Starting salary: £70,000–£80,000 (experience dependent)
* Competitive options package
* 33 days holiday plus bank holidays
* Hybrid working around core hours with office and R&D facilities in Lincolnshire
* Opportunity to join a founding-stage development team at one of the UK’s fastest-growing space autonomy startups
* Direct influence over autonomy system design, testing, and future mission capability
About Shield Space
Shield Space is a UK-founded orbital autonomy startup developing AI-enabled systems for secure and resilient space operations. Having recently secured significant investment, we are onboarding the founding technical team to turn this vision into reality. Drawing on heritage from UK Space Command and beyond, we are building guidance and decision systems that enable small satellites to act independently in orbit even under communications-denied conditions. Our mission is to establish the UK as a leader in autonomous orbital defence.
How to Apply
To apply, please send your CV to dmolland@shieldspace.co.uk along with a short 1–2 paragraph ‘Why Me’ statement outlining your experience in autonomy, reinforcement learning, or distributed systems, and why you believe you’d be the right fit for this role.
Application deadline: 23:59, Sunday 30th November