About the Role
We are a well-funded, enterprise-grade AI platform specialising in agent-based simulations and behavioral modeling — serving regulated industries including healthcare, finance, and education. Now part of a larger organisation accelerating agentic AI capabilities, we are growing our Research Tribe and hiring an Agent Systems Engineer to help design and build the core infrastructure that powers our platform at scale.
This is a high-ownership, high-impact role for an engineer who wants to go well beyond prompt chaining and work on production-grade, multi-agent systems from the ground up. Hybrid working is supported, with international location options considered for the right candidate.
What You'll Do
Design and implement long-running, harness-based multi-agent architectures — covering topologies, orchestration, memory management, tool registries, and execution environments.
Develop behavioral and persona models with goal-directed simulations, including evaluation frameworks, prompt schemas, and automated or human-in-the-loop feedback mechanisms to measure fidelity and surface failure modes.
Build signal and insight systems that translate agent outputs into actionable product decisions, enabling data-driven iteration across research, product, and engineering teams.
Ensure production reliability through comprehensive tracing, cost monitoring, failure detection, and robust fallback strategies.
Collaborate cross-functionally with distributed systems, machine intelligence, and product teams to deliver measurable, scalable agent capabilities.
What We're Looking For
Required:
5+ years of hands-on experience designing and implementing production-grade distributed systems and agent-based architectures (multi-agent topologies, orchestration, memory, tool registries, and execution) — this is a dealbreaker requirement.
Strong proficiency in Python, with substantial async programming experience.
Demonstrated experience building production ML systems, including tracing, cost monitoring, failure detection, and robust fallbacks.
Hands-on experience with containerisation and orchestration (Docker, Kubernetes) for large-scale agent infrastructures.
Experience designing behavioral models, goal-directed simulations, evaluation frameworks, prompt schemas, and human-in-the-loop feedback mechanisms.
Proven ability to translate agent outputs into actionable product decisions; experience building signal and insight systems.
Strong cross-functional communication and collaboration skills across technology, research, and product.
Nice to Have:
Background in or exposure to regulated industries (healthcare, finance, education).
Experience working at or with AI/ML tooling companies (e.g. agent orchestration, memory systems, ML evaluation platforms).
Comfort operating in a fast-moving, research-oriented environment with high individual ownership.
Compensation & Benefits
Salary: $180,000 – $250,000 USD annually (or equivalent, depending on location)
Visa sponsorship is not available for this role.
Location
Primarily based in London, UK, with hybrid working supported. International location options may be considered for exceptional candidates. This role is not fully remote.
Originally posted on