Computer Scientist for Touch-Labor Robotic Applications

Common Sense Robotics is a young startup based in Leuven, Belgium. We build robot systems for "touch labour" tasks in the manufacturing industries where the cost of failure is high and products and processes can be severely regulated; for example, aerospace, automotive and construction. These industries expect every robot decision to be traceable, auditable, and explainable.

We now need extra brains to develop our "Task Execution System": a hybrid neuro-symbolic AI architecture, integrating white-box, ontology-driven agents with modern AI agents, for task specification, world modelling, skill generation, motion control and task-directed active perception. The stack is built on the solid foundations of advanced control theory of force sensing and real-time computer vision for robotic manipulation. But it also needs to integrate Vision-Language-Action models. That approach allows us to integrate deep and reinforcement learning policies with time-proven control theory and symbolic reasoning, to realise highly reliable touch labour task executions that are fully predictable, inspectable, traceable and explainable.

Your role:

• Design, implement, document and formalize software architectures for multi-agent robotic systems, with low-latency and realtime sensor-based control systems as a special boundary case.
• Design, implement, document and formalize automatic code generation tools.
• Integrate your work with that of your colleagues responsible for other parts of the Task Execution System, such as the symbolic reasoning, the robotic motion control, and the development of applications and products.

Your ideal skill set, in the order of importance:

• You use Linux and other industry-grade open source software in all of your professional activities. You can tell the difference between a professional and an amateur software project.
• You have proven experience with C/C++ for low-latency and secure applications. You know how to integrate them with Python processes, with "the Web", and in robotic systems.
• You know how to exploit compilers' "intermediate representations" as one foundation for code generation and model-to-model transformations.
• You know where and why WASM can play a role in robotics systems.
• You know how to make embedded, "headless" systems, with several processes and threads that share memory buffers, in lock-free and wait-free versions.
• You know how to interact with such embedded systems remotely; for example via the Linux Trace Toolkit LLTNG.
• You know when and where low-latency streaming can be realised, and can motivate why you would select a particular framework (Zenoh, WebRTC, Media-over-Quic,...).
• You know how to deploy a multi-agent architecture over distributed hardware, how to monitor its operations, and how to "hot swap" some software components without having to reboot.
• You know what the impact is on distributed control systems of the "CAP Theorem" and the "Fallacies of distributed computing".
• You can write documentation in semantic HTML.

If this matches your expertise and ambitions, we look forward to your application.

How to apply: We don't review generic CVs. Instead, we expect you to send us a short application document, written specifically for this role, explaining why you're a good fit and proposing concretely how you would approach one or two of the challenges described in the "Your role" paragraph above.

Email: [email protected]