AI Platform Engineer

This is a principal-level, deeply hands-on AI platform engineering role for the most senior individual contributor responsible for the AI platform layer. This role owns the AI gateway architecture, the agent deployment pipeline infrastructure, and the Azure AI Foundry runtime configuration. The successful candidate will design and operate the infrastructure that makes AI engineering possible at enterprise scale, building the gateway that controls model traffic and enforcing deployment pipelines., Own and evolve the AI gateway architecture, configuring and operating the API gateway layer that manages traffic routing, rate limiting, authentication, quota enforcement, failover, and cost controls Own the agent deployment pipeline architecture, designing and operating the CI/CD infrastructure that moves AI agents from development through production Own and evolve the Azure AI Foundry runtime configuration, managing the project structure, model deployments, capacity allocations, and runtime parameters Design and enforce AI platform governance controls, including model access policies, quota management, and deployment approval gates Build and maintain AI platform observability, instrumenting the gateway, deployment pipelines, and Foundry runtimes with metrics, logging, and alerting Partner with the Senior Agent Architect and engineering teams to translate agent architecture requirements into platform infrastructure design Partner with the Principal Platform Engineer to design landing zone extensions and Azure infrastructure Partner with the DevSecOps Engineer to integrate AI model and agent deployments into the CI/CD pipeline Partner with the AI Security Lead to implement AI platform security controls Drive AI platform cost optimization and maintain comprehensive AI platform documentation Mentor AI platform and MLOps engineers, elevating platform engineering capability

8+ years of software, platform, or infrastructure engineering experience, including 3+ years of principal or senior-level ownership of AI/ML platform engineering, LLMOps, MLOps, or enterprise AI infrastructure Deep expertise in Azure AI Foundry, Azure OpenAI Service, or comparable enterprise LLM platform hosting and runtime management Demonstrated experience designing and operating API gateway architectures for AI model traffic Strong experience designing and operating CI/CD deployment pipelines for AI models, agents, or ML workloads Strong cloud engineering skills in Microsoft Azure, including networking, managed identity, Key Vault, Azure Monitor, Container Apps or AKS Experience implementing AI platform governance controls, including access policies, deployment approval workflows, and cost attribution Ability to set platform standards, influence architecture decisions, and drive AI platform quality Excellent written and verbal communication skills

Desired skills: Deep hands-on experience with Azure AI Foundry project management, model deployment configuration, capacity planning, and SDK integration at enterprise scale Experience with AI gateway solutions such as Azure API Management (APIM) with AI routing policies Experience in financial services, cybersecurity, or other regulated enterprise environments Experience with vector databases, embedding services, semantic cache layers, or RAG infrastructure components Experience with container orchestration (AKS, Azure Container Apps) for AI agent runtime hosting Familiarity with AI platform FinOps, including token cost tracking and model deployment rightsizing Experience with LangSmith, Weights & Biases, MLflow, or comparable AI platform observability and experiment tracking tools Microsoft Azure AI Engineer or Solutions Architect certifications