Senior Devops/Infrastructure Engineer

Overview

In this Senior DevOps/Infrastructure role, you will collaborate with Backend and ML/AI engineers to deploy and maintain dev/staging environments and run ML/AI pipelines and model deployments. You’ll design the telco deployment package in partnership with engineers and telco teams, enabling scalable, secure delivery. You will tackle production-grade observability, infrastructure as code, and GitOps practices to support carrier-scale Voice AI initiatives. This is a hybrid London-based opportunity with high ownership and impact on product strategy and execution.

Responsibilities

• Deploy and maintain dev/staging environments in collaboration with backend and ML/AI teams
• Design and implement telco deployment package with telco engineering teams
• Deploy ML models and maintain ML/AI pipelines on Kubernetes
• Set up and maintain CI/CD and GitOps workflows (Helm, ArgoCD)
• Implement monitoring and alerting for production systems (Prometheus/Grafana)
• Manage infrastructure as code and cloud resources (Terraform)
• Support GPU workloads on Kubernetes (drivers, scheduling, utilization)
• Ensure secrets management and least-privilege access across environments
• Experience deploying in air-gapped customer environments

Key requirements

• Experience with AWS and Kubernetes
• IaC experience with Terraform
• GitOps tooling experience (Helm, ArgoCD)
• Monitoring and alerting setup (Prometheus, Grafana)
• MLOps in Kubernetes (Kubeflow etc)
• Running GPU workloads on Kubernetes
• Familiarity with AI engineering
• Experience deploying in air-gapped environments
• Secrets management and least-privilege access across environments
• Desirable Azure experience
• Strong collaboration with cross-functional teams

• ownership and autonomy
• cross-functional collaboration
• problem solving and adaptability
• AWS
• Kubernetes
• Terraform

Full job description from WhatJobs. Apply for this role →