AI Platform Engineer

• Design, build, and maintain a scalable platform for serving LLM workloads in production
• Deploy and manage containerised workloads on Kubernetes, including GPU-based infrastructure
• Implement and optimise model serving solutions (e.g. vLLM, Triton, TGI)
• Set up monitoring and observability using tools such as Prometheus and Grafana
• Build and improve CI/CD pipelines and automate infrastructure using Python and Infrastructure as Code

• Strong experience with Kubernetes in production and solid Linux systems knowledge
• Hands-on experience with GPU infrastructure (e.g. NVIDIA A100/H100) and LLM/ML model serving
• Experience with CI/CD tools (Azure DevOps, GitLab CI, Jenkins) and Python scripting
• Familiarity with monitoring tools (Prometheus, Grafana) and infrastructure automation (Terraform, Ansible)
• Experience in regulated environments or cost optimisation for high-performance workloads is a plus
• We specifically need people who have worked with large language models and GPU-based inference at scale

Experience in regulated environments or cost optimisation for high-performance workloads is a plus