Role Overview
We are seeking a skilled Distributed Systems Engineer based in the UK to develop a small, paid proof-of-concept. The project involves crafting a minimal control plane for an edge inference network, focusing on node registration, heartbeats, routing, and failure/retry mechanisms. This role is not centered around machine learning or CRUD operations but requires strong systems thinking and adept failure handling.
Responsibilities
- Develop a proof-of-concept demonstrating a minimal control plane for an edge inference network.
- Implement node registration and management processes.
- Establish heartbeat protocols to ensure system reliability and performance monitoring.
- Design routing mechanisms and create strategies for failure detection and retry processes.
- Collaborate with stakeholders to align project objectives with technical solutions.
Required Skills
- Expertise in distributed systems engineering with a focus on control plane development.
- Strong understanding of node registration, heartbeat systems, and routing.
- Proficiency in designing robust failure detection and retry strategies.
- Demonstrated ability in systems thinking and handling complex system failures.
Nice to Have
- Experience with edge computing environments and inference networks.
- Familiarity with advanced routing protocols and network management.