Senior DevOps Engineer, AI Platform

We are looking for a hands-on Senior DevOps Engineer to build and operate the infrastructure powering our AI platforms, agent runtimes, web applications, backend services, APIs, and shared platform capabilities. Our environment includes a centralized LLM gateway, Python-based agent runtimes, RAG workers, MCP services, asynchronous processing, databases, caches, queues, and observability services.

You will work with AI engineers, application engineers, and architects who define technical designs, then independently translate those designs into reliable, scalable, secure, and observable production infrastructure across Microsoft Azure and Oracle Cloud Infrastructure.

What you’ll do

Translate application and platform technical designs into production ready cloud infrastructure with minimal supervision.

Design, provision, operate, and troubleshoot Kubernetes environments, primarily Azure Kubernetes Service and Oracle Kubernetes Engine.

Support AI workloads including LiteLLM based gateways, Python agent runtimes, RAG workers, MCP services, background workers, and asynchronous processing pipelines.

Design and manage ingress and egress networking, load balancers, DNS, TLS, private connectivity, routing, NAT, firewalls, network policies, and service to service communication.

Build and operate infrastructure for web applications and backend services, including APIs, databases, caches, queues, scheduled jobs, and event driven workloads.

Build and maintain CI/CD pipelines using Jenkins and Bitbucket, integrating Docker, Helm, Kubernetes, ArgoCD, and container registries.

Automate infrastructure provisioning and configuration using Terraform, Helm, Kubernetes manifests, Python, Bash, and related tooling.

Implement end to end observability using metrics, logs, distributed tracing, dashboards, alerts, health checks, and SLOs.

Own production readiness, incident troubleshooting, root cause analysis, scalability, reliability, and infrastructure cost optimization.

Create reusable infrastructure patterns that allow engineering teams to launch new services quickly and consistently.

What we’re looking for

7 or more years of experience in DevOps, SRE, Platform Engineering, Cloud Infrastructure, or a related role.

Strong hands on experience operating production Kubernetes environments and deep knowledge of networking, scheduling, storage, autoscaling, security, and troubleshooting.

Strong Microsoft Azure experience, including AKS, networking, identity, storage, and monitoring. OCI experience is preferred, or demonstrated ability to work across cloud providers.

Strong cloud networking knowledge across virtual networks, subnets, routing, NAT, load balancers, private networking, DNS, TLS, firewalls, ingress, and egress.

Strong experience with Jenkins, Bitbucket, Docker, Terraform, Helm, Kubernetes, and Infrastructure as Code.

Proven experience supporting production web applications and backend services, including REST APIs, microservices, background workers, and asynchronous architectures.

Hands on experience with databases, caching, and messaging systems such as PostgreSQL, Redis, RabbitMQ, or equivalent technologies.

Experience implementing production observability using OpenTelemetry, Grafana, Prometheus, Sentry, cloud monitoring, or similar tools.

Strong Linux, systems, and production troubleshooting skills.

Application engineering knowledge

You do not need to be a full time application developer, but you should understand how modern backend systems work and be able to troubleshoot across application and infrastructure boundaries.

Working knowledge of Python, especially backend services built with frameworks such as FastAPI.

Familiarity with at least one additional language such as C#, Java, Go, JavaScript, or TypeScript.

Understanding of HTTP, HTTPS, DNS, TCP/IP, proxies, authentication, APIs, connection pooling, caching, concurrency, queues, retries, dead letter queues, and asynchronous processing.

Ability to read application logs and stack traces and diagnose latency, memory, CPU, connection, and dependency issues.

How you’ll work

You will frequently receive a technical design for a new AI workload, application, backend service, or platform capability. From that design, you should be able to independently determine and implement the infrastructure needed to run it in production.

Determine the required cloud resources, Kubernetes configuration, namespaces, scaling model, and supporting services.

Configure ingress and egress, private connectivity, DNS, TLS, service communication, identities, and secrets.

Provision and operate dependencies such as PostgreSQL, Redis, RabbitMQ, storage, and other shared services.

Build the Jenkins and Bitbucket CI/CD flow for build, test, container publishing, deployment, validation, and rollback.

Define observability, health checks, dashboards, alerts, capacity monitoring, and operational runbooks before production launch.

Own infrastructure delivery through UAT and production, partnering with architects and engineers when design tradeoffs require discussion.

What will make you stand out

Experience supporting AI or machine learning platforms, LLM gateways, agent runtimes, RAG pipelines, or MCP services.

Experience with Cloudflare, Envoy, ArgoCD, GitOps, and OpenTelemetry.

Experience building reusable infrastructure platforms for high scale SaaS or customer facing applications.

Experience operating distributed backend systems using RabbitMQ, Redis, PostgreSQL, and similar technologies.

AI or machine learning infrastructure experience is helpful, but not required. Strong experience with Kubernetes, web and backend infrastructure, networking, queues, databases, CI/CD, observability, and production cloud operations is the foundation for this role.

#NetworkSolutions