Infrastructure / Platform Engineer (London)

Job summary

Own and scale production cloud infrastructure and inference systems for low-latency voice AI, balancing reliability, performance, scalability, and cost. Build and improve infrastructure across GCP and GPU cloud providers using Kubernetes, Docker, and Terraform, while optimising model inference, automating deployments, and monitoring production systems. The role also includes incident response and supporting secure enterprise deployments.

Qualifications

• Experience building and operating production cloud infrastructure at scale.
• Hands-on experience with GCP, Kubernetes, Docker, Terraform, and Python.
• Experience with CI/CD, monitoring, observability, and production incident response.
• Understanding of infrastructure performance, scalability, and cost optimisation.
• Experience participating in on-call rotations or taking responsibility for production incidents.
• Proactive approach to identifying bottlenecks and improving production systems.
• Ability to work autonomously, make architectural decisions, and take ownership of critical systems.
• Experience with AI/ML inference, GPU infrastructure, or vLLM is preferred.
• Experience hosting audio, speech, or real-time AI applications is preferred.
• Experience with C++ is preferred.
• Familiarity with SOC 2, ISO 27001, or other security compliance frameworks is preferred.
• Experience with private cloud or on-premise enterprise deployments is preferred.

Responsibilities

• Build, manage, and scale production infrastructure across GCP and GPU cloud providers.
• Optimise inference latency, throughput, GPU utilisation, and infrastructure costs through profiling and experimentation.
• Identify and resolve bottlenecks in model building, deployment, and serving.
• Monitor critical systems, respond to incidents, and help maintain reliable service outside UK working hours.
• Improve deployment pipelines, infrastructure automation, monitoring, and observability.
• Support secure infrastructure practices and enterprise deployment requirements.
• Make infrastructure architecture decisions balancing scalability, reliability, performance, and cost.

Skills

Work schedule

Industry

Relocation