Infrastructure / platform engineer for AI inference

Neuphonic is building the next generation of voice AI, making natural, real-time speech accessible across devices, languages, and applications. We're a small, ambitious team of researchers and engineers building technology used by developers and businesses around the world. As our customer base grows, we need to scale our production infrastructure while maintaining the performance, reliability, and low latency that our products depend on. We're looking for an Infrastructure / Platform Engineer to take ownership of our cloud infrastructure and inference systems.

• Build, manage, and scale our production infrastructure across GCP and GPU cloud providers using Kubernetes, Docker, and Terraform.
• Continuously improve inference performance, latency, throughput, GPU utilisation, and infrastructure costs through profiling, experimentation, and iteration, rather than simply maintaining the status quo.
• Identify bottlenecks and inefficiencies in how we build, deploy, and serve models, and take ownership of implementing improvements.
• Monitor critical systems, respond to incidents, and help ensure reliable service for our customers outside UK working hours.
• Make autonomous technical decisions that balance scalability, reliability, performance, and cost.
• Improve deployment pipelines, infrastructure automation, monitoring, and observability.
• Support secure infrastructure practices and enterprise deployment requirements.

• Strong experience building and operating production cloud infrastructure at scale, ideally supporting applications with significant user traffic.
• Hands-on experience with GCP, Kubernetes, Docker, Terraform, and Python.
• Experience with CI/CD, monitoring, observability, and production incident response.
• A strong understanding of infrastructure performance, scalability, and cost optimisation.
• Experience participating in on-call rotations or taking responsibility for production incidents.
• A proactive approach to engineering, with experience identifying bottlenecks, experimenting with improvements, and optimising production systems.
• Comfortable working autonomously, making architectural decisions, and taking ownership of critical systems.
• Будет плюсом: Experience with AI/ML inference, GPU infrastructure, or vLLM; Experience hosting audio, speech, or real-time AI applications; Experience with C++; Familiarity with SOC 2, ISO 27001, or other security compliance frameworks; Experience with private cloud or on-premise enterprise deployments

• Условий в вакансии нет