AgentOps Platform Senior Engineer — Azure AI Infrastructure & Operations

We're hiring an AgentOps Platform Senior Engineer — Azure AI Infrastructure & Operations for a professional services firm with 60+ years of experience delivering accounting, tax, and advisory services across government, healthcare, franchise, and construction sectors.

Our client is seeking a hands-on Azure AI Platform Infrastructure and Operations Engineer to own the reliability, scalability, observability, and cost efficiency of the cloud foundation that powers enterprise Agentic AI solutions. This role is ideal for a senior engineer who can work directly in the Azure environment—configuring services, tuning infrastructure, automating deployment patterns, monitoring platform health, and resolving performance bottlenecks across AI workloads, agent runtimes, model endpoints, data pipelines, retrieval systems, and integration services. The successful candidate will ensure the infrastructure layer is production-ready, resilient, secure, and optimized for high-scale agentic operations.

Position Summary

Our client is a leading accounting and consulting firm and seeks an experienced Azure AI cloud platform engineer to operate and continuously optimize the infrastructure layer for their next-generation Agentic AI platform. This role will be directly accountable for Azure AI Foundry, Azure OpenAI, AKS, Container Apps, App Services, Azure Functions, API Management, networking, identity, observability, DevOps automation, data services, and supporting platform components required to run intelligent agents at enterprise scale. The engineer will partner with product, architecture, security, and application teams while remaining deeply hands-on in implementation, operations, performance tuning, and incident resolution.

Azure AI Platform Operations & Infrastructure Engineering

• Operate and optimize Azure infrastructure supporting Agentic AI workloads, including Azure AI Foundry, Azure OpenAI, AKS, Azure Container Apps, App Services, Azure Functions, Azure API Management, Azure AI Search, Cosmos DB, Redis, storage, networking, and monitoring services.
• Own platform reliability, scalability, latency, throughput, token utilization, capacity planning, and cost optimization across production AI workloads.
• Implement infrastructure automation using Bicep, Terraform, Azure DevOps, GitHub Actions, policy-as-code, and repeatable deployment patterns.
• Troubleshoot and resolve production issues across compute, networking, identity, model endpoints, retrieval pipelines, agent orchestration layers, and integration services.

Scalable Azure Architecture for Agentic AI

• Design and implement cloud-native operating patterns for agent workloads, including containerized execution, serverless workflows, managed hosting options, autoscaling, workload isolation, and resilient production deployment models.
• Engineer the platform for high availability and graceful degradation across agent runtimes, orchestration services, tool connectors, vector stores, grounding data services, and model-serving endpoints.
• Define landing-zone patterns, subscription/resource group structure, network segmentation, private endpoints, DNS, managed identities, RBAC, secrets management, and policy controls for AI platform services.
• Apply Azure Well-Architected principles for reliability, security, cost optimization, operational excellence, and performance efficiency across the AI infrastructure layer.

Multi-Tenancy & SaaS Architecture

• Architect multi-tenant B2B environments with tenant-aware data partitions using Cosmos DB and Azure AD B2C/Entra ID to ensure data, security, and cost isolation.
• Build per-tenant vector stores, knowledge bases, and connectors to support customer-specific document ingestion and retrieval.

Agentic AI Runtime, Observability & Performance

• Support production agent runtimes built with Microsoft Agent Framework, Semantic Kernel, LangChain, AutoGen, or comparable orchestration frameworks.
• Implement end-to-end observability for agents, including traces, prompts, responses, tool calls, retrieval activity, token usage, latency, failures, quality signals, and cost metrics.
• Configure Azure Monitor, Log Analytics, Application Insights, dashboards, alerts, workbooks, distributed tracing, and operational runbooks for Agentic AI workloads.
• Continuously tune infrastructure performance for agent execution, model invocation, retrieval-augmented generation, tool orchestration, concurrent user load, and long-running workflows.
• Partner with engineering teams to operationalize evaluation loops, drift monitoring, regression detection, and release gates for agent quality, reliability, and safety.

Capacity, FinOps & Platform Optimization

• Establish capacity models for Azure OpenAI, model endpoints, embeddings, vector search, agent runtimes, compute pools, message queues, and integration services.
• Optimize infrastructure cost through right-sizing, autoscaling, quota management, reserved capacity planning, model routing, caching, batching, token controls, and workload scheduling.
• Monitor and report operational health, platform utilization, service limits, consumption trends, saturation points, and remediation plans for AI platform leadership.
• Drive proactive improvements to reduce latency, increase throughput, improve resiliency, and maintain predictable operating costs as agent adoption grows.

Full Stack Management

• End-to-End Application Development: Design, develop, and maintain robust, scalable, and secure full-stack web applications.
• Frontend Development: Build dynamic and responsive user interfaces using React, TypeScript, and modern state management libraries.
• Backend & API Development: Architect and implement scalable backend services and RESTful APIs using Python (with frameworks like FastAPI or Flask) and caching technologies like Redis.
• Database Management: Design and manage data models and interact with both relational (SQL) and NoSQL databases (e.g., Cosmos DB).

Data Engineering & Processing

• Lead the design and implementation of robust data ingestion, transformation, and processing pipelines using Azure Data Factory, Databricks, Synapse, or equivalent.
• Ensure data quality, governance, and compliance with enterprise and regulatory standards.
• Develop secure pipelines for fine-tuning data preparation, ensuring data labeling, anonymization, and quality scoring to meet Responsible AI standards.

Security, Compliance & Reliability

• Champion security best practices, including identity management, data protection, and compliance (e.g., SOC2, GDPR).

Stakeholder Engagement & Communication

• Act as a technical liaison between engineering, product, business, and executive teams.
• Communicate complex technical concepts clearly to non-technical stakeholders.

Required Qualifications

• 7+ years of hands-on cloud infrastructure, platform engineering, DevOps, SRE, or production operations experience, with significant depth in Microsoft Azure.
• Direct experience operating production Azure workloads using services such as Azure AI Foundry, Azure OpenAI, AKS, Azure Container Apps, App Services, Azure Functions, Azure API Management, Azure Monitor, Application Insights, Log Analytics, Azure AI Search, Cosmos DB, Redis, Key Vault, Storage, and Entra ID.
• Strong understanding of cloud-scale architecture, networking, identity, RBAC, private connectivity, secrets management, resiliency patterns, autoscaling, disaster recovery, and secure deployment practices.
• Proficiency with Infrastructure as Code and CI/CD automation using Bicep, Terraform, Azure DevOps, GitHub Actions, YAML pipelines, containers, and Kubernetes operating patterns.
• Practical experience supporting GenAI, RAG, vector search, prompt orchestration, agent frameworks, model endpoints, telemetry, and cost controls in production environments.
• Ability to diagnose and remediate production issues across Azure infrastructure, application services, AI services, data services, APIs, authentication, networking, and observability tooling.
• Experience building dashboards, alerts, SLOs, operational runbooks, incident response workflows, and reliability reporting for mission-critical cloud platforms.
• Strong scripting or engineering skills in Python, PowerShell, Bash, or equivalent automation languages.
• Working knowledge of containerization, Kubernetes, Docker, Helm, KEDA, ingress patterns, service mesh concepts, workload identity, and secure runtime configuration.
• Understanding of AI workload operations, including token consumption, model latency, quota limits, evaluation telemetry, drift detection, grounding quality, and retrieval performance.
• Knowledge of enterprise security, compliance, governance, and Responsible AI controls applicable to cloud-hosted AI platforms.
• Proven ability to work directly with architecture, product, security, engineering, and operations teams to move AI workloads from pilot to production.
• Excellent communication skills with the ability to explain infrastructure tradeoffs, operational risk, and platform health to technical and executive stakeholders.
• Experience working in Agile, Scrum, Kanban, DevOps, or SRE operating models.

Preferred Qualifications

• Bachelor’s degree in Computer Science, Engineering, Information Systems, Cloud Computing, or a related field, or equivalent practical experience.
• Azure certifications such as Azure Solutions Architect Expert, Azure DevOps Engineer Expert, Azure Administrator Associate, Azure Security Engineer Associate, or AI Engineer Associate.
• Working knowledge of Microsoft Agent Framework, Semantic Kernel, LangChain, AutoGen, Azure AI Foundry agents, and enterprise agent observability patterns.
• Experience implementing Azure landing zones, hub-and-spoke networking, private endpoints, Azure Policy, Defender for Cloud, workload identity, managed identities, and key management patterns.
• Experience operating multi-tenant SaaS platforms, tenant-aware isolation models, metering, chargeback/showback, cost allocation, and capacity planning.
• Experience with production-grade RAG infrastructure, including Azure AI Search, embeddings, vector indexes, document ingestion pipelines, retrieval quality monitoring, and grounding data governance.
• Hands-on experience with OpenTelemetry, distributed tracing, Application Insights, Log Analytics queries, Azure Monitor alerts, dashboards, and reliability engineering practices.
• Experience with FinOps practices for AI workloads, including token optimization, model selection tradeoffs, quota management, caching strategies, and usage-based cost forecasting.
• Experience supporting regulated, security-sensitive, or client-facing enterprise AI platforms where auditability, data protection, access control, and operational consistency are required.