AI Platform Engineer

Job Description Roles & Responsibilities Cloud AI Services Hands-on production experience with Microsoft Azure AI Services including Azure OpenAI, Azure AI Foundry-related services, Azure AI Search, Azure Speech, Document Intelligence, and Content Safety and equivalent fluency with AWS AI Services, including AWS Bedrock and supporting model and content services. Familiarity with Core42 Compass for in-region inference is required. Agentic AI Frameworks Strong working knowledge of Microsoft Agent Framework and LangGraph, including agent orchestration, tool calling, skill composition, memory and state management, planning patterns, multi-agent execution topologies, and human-in-the-loop checkpoints. Ability to read and reason about agent graphs, conditional edges, retry policies, and tool schemas to diagnose execution-level issues quickly. LLM Operations Practical expertise in prompt-level troubleshooting, token consumption analysis, context-window management, model configuration tuning, endpoint health monitoring, Azure OpenAI PTU capacity and quota management, throttling and latency analysis, fallback handling, and responsible-AI controls including content filtering and safety policies. Kubernetes and Containers Deep operational experience with Azure Kubernetes Service, including Kubernetes core constructs (deployments, pods, services, ingress, namespaces, ConfigMaps, secrets), Helm-based release management, autoscaling behaviour, container troubleshooting, and Docker image lifecycle. Comfort with kubectl, kustomize, and platform-level network and identity constructs. API and MCP Gateway Strong expertise in Azure API Management, including API policies, named values, products, subscriptions, OAuth 2.0 and OpenID Connect flows, managed identities, JWT validation, rate limiting, caching, and backend routing. Working knowledge of REST APIs and event-driven integration patterns. Specific experience with the Model Context Protocol (MCP) including MCP servers, MCP clients, tool definitions, and gateway-mediated MCP patterns is highly desirable. Observability Expertise in Comet Opik for distributed agent and prompt tracing, including trace inspection, evaluation runs, drift detection, and dashboard construction. Strong working knowledge of Azure Monitor, Application Insights, Log Analytics, and AWS CloudWatch, with the ability to construct correlated views across logs, metrics, traces, and business indicators using correlation identifiers. DevOps and Automation Comfort with Git-based workflows, CI/CD pipelines (GitLab CI/CD or Azure DevOps), infrastructure as code (Terraform or Bicep), release automation, and deployment validation. Strong scripting in Python, PowerShell, and Bash for operational tooling, log mining, and remediation automation. Voice AI Working experience with ElevenLabs APIs and SDKs, voice-agent integrations, real-time audio processing, session-level troubleshooting, latency and audio-quality analysis, and integration with conversational AI and telephony layers. Security and Governance Hands-on experience with Microsoft Entra ID, RBAC, managed identities, Azure Key Vault, secrets and certificate management, private networking and Private Link, vulnerability management, audit logging, data protection controls, and AI governance frameworks including model access management and responsible-AI policy enforcement. Service Management Practical application of ITIL practices including incident management, problem management, change management, service requests, SLA and OLA management, root-cause analysis, and major incident management within an enterprise service-management toolset such as ServiceNow. Desired Candidate Profile The following certifications are considered desirable: ▪ Microsoft Azure Administrator or Azure Solutions Architect Expert ▪ Microsoft Azure AI Engineer Associate ▪ AWS Solutions Architect or AWS Certified Machine Learning Specialty ▪ Certified Kubernetes Administrator (CKA) or Certified Kubernetes Application Developer (CKAD) ▪ ITIL Foundation or higher ▪ DevOps, Site Reliability Engineering, Cybersecurity, or AI Governance certifications from a recognized body Employment Type Full-time Company Industry IT - Software Services Department / Functional Area IT Software Keywords AI Platform EngineerGenAIGenerative AIAI PlatformLLMOpsAzure OpenAIAzure AI FoundryAWS BedrockLangGraphAgentic AIKubernetesAKSAzure API ManagementMCPModel Context ProtocolAzure AI SearchPythonTerraformAzure DevOps Get real-time job updates only on our App