Senior Infrastructure Engineer - Kubernetes and MLOps

Ventula Consulting; Greater London; Híbrido; GBP 100.000 - 150.000; Jornada completa

Descripción de la vacante

Ventula Consulting Ltd. is hiring its first dedicated infrastructure engineer to design how the platform is deployed and upgraded inside telco networks.

You will own dev and staging infrastructure on AWS (plus some Azure) and a Kubernetes GitOps setup with ArgoCD and Helm, while supporting ML pipelines and building robust monitoring and incident response. You’ll set infrastructure standards from day one and define how voice AI gets deployed into carrier networks, with a salary between £100k -

Formación

• Experience deploying platforms in production.
• Ability to own deployment pipelines and infrastructure standards.
• Comfort working in a small team with some ambiguity.

Responsabilidades

• Design how the platform is deployed and upgraded inside telco networks.
• Own dev and staging infrastructure on AWS (and some Azure) with a Kubernetes GitOps setup (ArgoCD, Helm).
• Support ML pipelines and model deployment with the ML/AI team.
• Build monitoring, alerting, runbooks and incident response.

Conocimientos

Ownership

Ambiguity tolerance

Herramientas

AWS

Kubernetes

Terraform

Helm

ArgoCD

Prometheus

Grafana

Descripción del empleo

London · Hybrid, 3 days a week in the office

AI company that protects people from fraud and scam calls. It's a joint venture founded by several of the world's leading telecom operators, and it's hiring its first dedicated infrastructure engineer.

The ideal person has already taken a product from zero to 100,000 users and built the infrastructure that got it there: the first cluster, the first pipelines, the first alerts, and keeping it all reliable as usage grew.

What you'll do

• Design how the platform is deployed and upgraded inside telco networks, working with operators' engineering teams
• Own dev and staging infrastructure on AWS (some Azure) and a Kubernetes GitOps setup (ArgoCD, Helm)
• Support ML pipelines and model deployment alongside the ML/AI team
• Build monitoring, alerting, runbooks and incident response

What you'll bring

• AWS, Kubernetes, Terraform, Helm and ArgoCD in production
• Production monitoring and alerting (Prometheus/Grafana or similar)
• Ownership and comfort with ambiguity in a small team
• Nice to have: air-gapped deployments, Azure, MLOps or GPU workloads on Kubernetes, secrets management and least-privilege access.

You’ll set the infrastructure standards from day one and define how voice AI gets deployed into carrier networks.

This role is offering a salary between £100k - £150k and the package is benchmarked to attract senior, top-tier talent.