Sr AI Operations Engineer

Key Responsibilities

AI Platform Operations

• Operate and maintain enterprise AI platforms and services across development, test, and production environments.

• Support Azure OpenAI, Azure AI Foundry, Azure Machine Learning, and related Azure AI platform services.

• Operate the application hosting platform for AI services across Azure App Service, Azure Functions, and Azure Container Apps, including networking, scaling, and runtime configuration.

• Ensure platform availability, performance, reliability, scalability, and operational stability.

• Perform platform configuration, lifecycle management, upgrades, and operational maintenance.

  AI Service Deployment Operations

• Deploy and operationalize AI and Generative AI workloads in controlled enterprise environments.

• Support production AI solutions including copilots, AI assistants, chatbots, agentic applications, retrieval-augmented generation (RAG) services, and machine learning applications.

• Manage release activities, prompt and model version control, runtime configurations, deployment validations, and operational handovers.

• Deploy and operate machine learning models and endpoints developed by Data Science teams, providing the pipelines, environments, and runtime platform they promote through.

• Troubleshoot deployment, integration, performance, and runtime issues across AI services.

  Container Kubernetes Platform

• Support containerised AI workloads using Docker and Kubernetes operational best practices, including image build, hardening, registries, and runtime configuration.

• Help design, build, and operate Azure Kubernetes Service environments as the container platform is introduced for AI and platform workloads.

• Establish and monitor cluster health, capacity, autoscaling, networking, ingress, security policies, and operational readiness.

• Contribute to platform resiliency, backup, recovery, and disaster recovery readiness.

  Model Access Gateway Operations

• Operate the governed model-access layer serving AI applications, agents, and developer tooling - provider routing, failover, model catalogue, and version management across Azure OpenAI, AWS Bedrock, and Google Vertex AI.

• Manage model access control, user and application entitlements, quota allocation, rate limiting, and credential provisioning for the gateway.

• Monitor and attribute token consumption, throttling and 429 events, latency, and cost by model, application, and consumer.

• Support gateway upgrades, provider onboarding, configuration changes, and controlled rollout of new model versions.

  Monitoring and Observability

• Implement monitoring, logging, alerting, dashboards, and operational metrics for AI platforms and services.

• Monitor AI system utilization, availability, latency, cost consumption, token usage, and performance trends.

• Monitor AI-specific signals including model and agent quality, quota and throttling events, data or model drift, and grounding index freshness.

• Use Azure Monitor, Application Insights, Log Analytics, and OpenTelemetry instrumentation to identify incidents and improvement areas.

• Provide operational insights to engineering, security, governance, and leadership stakeholders.

  Incident Problem Management

• Investigate and resolve platform incidents, production issues, service disruptions, and operational risks.

• Perform root cause analysis and document corrective and preventive actions.

• Support production support processes, escalation management, and incident communications.

• Participate in post-incident reviews and implement service reliability improvements.

  Operational Excellence

• Create and maintain runbooks, support procedures, platform documentation, and operational knowledge articles.

• Automate recurring support, validation, monitoring, and deployment activities.

• Continuously improve platform efficiency, stability, security posture, and cost governance.

• Support service-level objectives and operational performance targets for AI platforms.

  Cloud Engineering Automation

  Infrastructure as Code

• Develop and maintain Infrastructure as Code using Terraform, including reusable modules, remote state management, validation, and peer review.

• Automate Azure AI platform provisioning, configuration, policy enforcement, and environment standardization across development, test, and production.

• Manage controlled promotion of infrastructure changes across environments, with drift detection, change tracking, and infrastructure compliance.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.