Software Engineer · Agent Runtime

Own the execution engine that runs customer agent workflows and multi-agent swarms in production. This staff-level role covers orchestration, scheduling, state management, tool use, human-in-the-loop controls, and the reliability characteristics required for a core platform service. The position is based in London or available remotely, with broad technical influence across the platform engineering group.

• Design and implement the runtime responsible for agent and swarm execution, scheduling, state transitions, and tool calls.
• Build human-in-the-loop gates and control points that allow workflows to pause, seek approval, or safely resume.
• Make orchestration reliable, observable, recoverable, and diagnosable under partial failure and changing workloads.
• Define stable runtime APIs and abstractions for applied-AI and forward-deployed engineering teams.
• Establish engineering standards for API design, failure handling, testing, operability, and production readiness.
• Provide technical leadership and mentorship as the platform team grows.

• Deep experience with distributed systems and backend engineering, especially reliable execution or orchestration services.
• Track record of designing systems that manage state, scheduling, retries, failures, and recovery in production.
• Strong judgment around API design, observability, operational behavior, and fault handling.
• Experience with large-language-model or agent runtimes is valuable, though the core requirement is robust systems engineering.
• Staff-level technical leadership, including the ability to set direction across teams and raise engineering quality.
• Effective mentorship and communication skills for working with engineers across platform and applied product areas.

• Staff full-time role with London or remote working options.
• Remote-friendly arrangements across the UK, EU, and selected global time zones.
• Equity participation and cash compensation benchmarked to leading London and remote markets.