Platform Engineer

Role overview

Own the deployment and serving platform for private AI workspaces used by professional-services firms. Each customer runs in a dedicated environment with separate infrastructure and data stores, so the role focuses on repeatable deployments, demonstrable tenant isolation, responsive model access, and safe ongoing upgrades.

Responsibilities - Build and operate the end-to-end process for provisioning single-tenant deployments. - Maintain and verify separation between customer instances, data stores, keys, and logs. - Manage latency and cost in the service path connecting workspaces to external model providers. - Roll out upgrades across deployments while avoiding unplanned customer downtime. - Instrument the platform so performance changes and regressions can be measured.

Requirements - Substantial experience operating latency-sensitive production systems relied on by others. - Practical ownership of infrastructure as code, secrets, and identity systems. - Experience running a shared technology stack for multiple tenants and understanding its failure modes. - A measurement-led approach, including benchmarking to inform engineering decisions.

Nice to have - Experience with UK or EU data residency needs for regulated customers. - Security engineering experience or familiarity with security reviews and questionnaires. - Open-source contributions to deployment, model-serving, or observability tools.

Benefits and work setup - Full-time platform role based in London or remote during UK/EU working hours.