Walker Healthforce
AIOps Engineer – Agentic AI, MLOps & Azure Cloud | Hybrid | Contract
Apply now# of openings: 1
# of submission slots: 3
Job title: AIOps Engineer – Agentic AI, MLOps & Azure Cloud
Location: Hybrid, onsite in St. Louis, MO 3 days a week.
Shift/Schedule:
Start date: 11/23/2026
Contract length: 11/23/2026 – 07/30/2027
BR: $100
Job Posting ID: DLTJP00065052
Role description:
Seeking an experienced AIOps Engineer with strong hands-on expertise in agentic AI, large language models (LLMs), MLOps, Python backend development, Kubernetes, and Microsoft Azure cloud infrastructure.
The engineer will design, develop, deploy, and maintain production-grade AI and machine learning solutions, including LLM agents, multi-agent workflows, retrieval-augmented generation (RAG) pipelines, and scalable machine learning platforms.
This role combines AI application engineering, AgentOps, MLOps, cloud platform engineering, and operational support. The successful candidate will build reliable AI services, implement observability and evaluation frameworks, automate deployments, and establish reusable standards for AI workloads.
Responsibilities include developing AI agents using frameworks such as LangGraph, LangChain, CrewAI, and AutoGen; building Model Context Protocol (MCP) servers; and implementing prompt versioning, agent tracing, evaluation frameworks, guardrails, and cost monitoring.
The engineer will also develop and operationalize classical machine learning models, including regression, classification, time-series forecasting, and anomaly detection, while managing model deployment, monitoring, experiment tracking, and retraining workflows.
Strong Python and FastAPI development skills are required, along with experience implementing secure REST APIs, microservices, OAuth2, JWT, RBAC, and enterprise security controls.
The successful candidate will support AI workloads on Kubernetes, preferably Azure Kubernetes Service (AKS), and manage CI/CD pipelines, Docker containers, cloud infrastructure, and infrastructure-as-code deployments.
The role also requires strong platform support, troubleshooting, documentation, and stakeholder communication skills.
This is a fully remote contract opportunity.
Required experience:
-
3–6 years of software engineering or platform engineering experience.
-
At least 2 years of experience focused on AI/ML systems.
-
Advanced Machine Learning / AI experience aligned with the posting's 6–9-year classification.
-
Strong hands-on Python development experience.
-
Experience developing clean, testable, production-grade Python applications.
-
Hands-on FastAPI experience, including REST API development, dependency injection, middleware, and asynchronous programming patterns.
-
Experience designing and maintaining microservices architectures.
-
Experience implementing API security using OAuth2, JWT, and RBAC.
-
Experience implementing API rate limiting and security controls.
-
Experience developing LLM-powered applications.
-
Experience building AI agents, tool-calling workflows, function-calling capabilities, and RAG pipelines.
-
Hands-on experience with at least one agentic framework: LangGraph, LangChain, CrewAI, or AutoGen.
-
Experience developing or supporting MCP servers.
-
Understanding of prompt engineering and prompt versioning.
-
Experience evaluating LLM outputs and supporting AI red-teaming practices.
-
Familiarity with agent observability tools such as LangSmith, Phoenix/Arize, or Weights & Biases.
-
Experience implementing agent tracing, cost tracking, guardrails, and evaluation frameworks.
-
Experience monitoring token usage, tool-call failures, and agent performance.
-
Experience building and operating production machine learning pipelines.
-
Experience supporting ML workflows from data ingestion and feature engineering through deployment and monitoring.
-
Working knowledge of classical machine learning techniques, including regression, classification, time-series forecasting, and anomaly detection.
-
Experience using MLflow or Azure Machine Learning for experiment tracking, model registry, or model serving.
-
Experience monitoring model performance, data drift, and concept drift.
-
Experience supporting model retraining workflows.
-
Experience applying machine learning to operational use cases such as incident prediction, log anomaly detection, and root-cause analysis.
-
Experience operating containerized workloads using Docker.
-
Experience supporting Kubernetes-based workloads.
-
Experience with Kubernetes deployments, Helm charts, autoscaling, resource quotas, or namespace management.
-
Experience supporting Microsoft Azure cloud infrastructure.
-
Experience developing or maintaining CI/CD pipelines using GitHub Actions or Azure DevOps.
-
Experience implementing infrastructure as code using Terraform or Bicep.
-
Experience supporting platform incidents, environment provisioning, and access management.
-
Experience developing runbooks, architecture diagrams, SOPs, and release documentation.
-
Strong troubleshooting, analytical, communication, and cross-functional collaboration skills.
Required skills:
-
AIOps
-
Agentic AI
-
AgentOps
-
Large Language Models (LLMs)
-
LLM Agents
-
Multi-Agent Workflows
-
LangGraph
-
LangChain
-
CrewAI
-
AutoGen
-
Model Context Protocol (MCP)
-
Retrieval-Augmented Generation (RAG)
-
Prompt Engineering
-
Prompt Versioning
-
LLM Evaluation
-
AI Guardrails
-
Agent Tracing
-
Agent Observability
-
Token Usage Monitoring
-
AI Cost Tracking
-
Tool-Call Failure Analysis
-
MLOps
-
Machine Learning Pipelines
-
Model Deployment
-
Model Monitoring
-
MLflow
-
Azure Machine Learning
-
Regression
-
Classification
-
Time-Series Forecasting
-
Anomaly Detection
-
Data Drift
-
Concept Drift
-
Model Retraining
-
Python
-
FastAPI
-
REST APIs
-
OpenAPI
-
Microservices
-
Asynchronous Programming
-
OAuth2
-
JWT
-
RBAC
-
API Security
-
Rate Limiting
-
Azure Key Vault
-
Secrets Management
-
Audit Logging
-
Kubernetes
-
Azure Kubernetes Service (AKS)
-
Helm
-
HPA
-
KEDA
-
Docker
-
GitHub Actions
-
Azure DevOps
-
CI/CD
-
Microsoft Azure
-
Infrastructure as Code
-
Terraform
-
Bicep
-
Platform Support
-
Incident Management
-
Root-Cause Analysis
-
Technical Documentation
-
Runbooks
-
SOPs
-
Stakeholder Communication
Required education:
Required certs/licenses:
Preferred experience/skills:
-
Experience operating AI workloads on Azure Kubernetes Service (AKS).
-
Experience developing reusable agentic workflow templates and deployment standards.
-
Experience implementing MCP servers and advanced RAG architectures.
-
Experience using LangSmith, Phoenix/Arize, or Weights & Biases for agent observability.
-
Experience implementing automated ML evaluation gates and retraining triggers within CI/CD pipelines.
-
Experience using Azure Machine Learning for model lifecycle management.
-
Experience implementing Kubernetes autoscaling using HPA or KEDA.
-
Experience using Terraform or Bicep to automate Azure infrastructure provisioning.
-
Experience applying AI/ML techniques to incident prediction, anomaly detection, and operational root-cause analysis.
-
Experience supporting enterprise AI platforms with established security, governance, and documentation standards.
Primary responsibilities:
-
Build and deploy LLM agents and multi-agent workflows using LangGraph, LangChain, CrewAI, or AutoGen.
-
Develop and maintain Model Context Protocol (MCP) servers.
-
Design and implement retrieval-augmented generation (RAG) pipelines.
-
Implement agent tracing, prompt versioning, evaluation frameworks, and guardrails.
-
Monitor token usage, AI costs, tool-call failures, and agent performance.
-
Identify and address agent drift and reliability issues.
-
Standardize reusable agentic workflow templates and engineering practices.
-
Design and develop end-to-end machine learning pipelines.
-
Support data ingestion, feature engineering, model training, deployment, and monitoring.
-
Productionize regression, classification, time-series forecasting, and anomaly detection models.
-
Manage experiment tracking, model registries, and model serving using MLflow or Azure Machine Learning.
-
Apply data science techniques to incident prediction, log anomaly detection, and root-cause analysis.
-
Monitor deployed models for data drift, concept drift, and performance degradation.
-
Implement model retraining workflows.
-
Design and develop Python REST APIs using FastAPI.
-
Implement event-driven integrations and OpenAPI documentation.
-
Apply OAuth2, JWT, RBAC, and API rate limiting.
-
Implement secrets management using Azure Key Vault.
-
Maintain audit logging and security controls across AI services.
-
Design and maintain microservices architectures for AI workloads.
-
Deploy and operate AI workloads on Kubernetes.
-
Support AKS deployments, Helm charts, autoscaling, resource quotas, and namespace management.
-
Develop CI/CD pipelines using GitHub Actions and Azure DevOps.
-
Integrate ML evaluation gates and automated retraining triggers into deployment workflows.
-
Build and optimize Docker images and manage container registries.
-
Provision and maintain Azure infrastructure, including VMs, AKS, storage, networking, and IAM.
-
Implement infrastructure as code using Terraform or Bicep.
-
Support access requests, environment provisioning, and platform incidents.
-
Troubleshoot platform issues and document root causes and resolutions.
-
Develop and maintain runbooks, architecture diagrams, SOPs, and release notes.
-
Support access reviews, usage reporting, and platform health updates.
-
Communicate AI workload performance and operational issues to stakeholders.
-
Maintain versioned, accessible technical documentation.
-
Promote reusable engineering practices and operational improvements.
Ideal candidate:
An experienced AIOps Engineer with strong Python development skills and practical experience deploying production-grade AI/ML solutions.
The ideal candidate has 3–6 years of software or platform engineering experience, including at least 2 years working with AI/ML systems.
This individual has hands-on experience building LLM agents and RAG pipelines using frameworks such as LangGraph, LangChain, CrewAI, or AutoGen, along with knowledge of MCP servers, agent observability, prompt evaluation, and guardrails.
The successful candidate also brings strong MLOps capabilities, including production ML pipelines, experiment tracking, model deployment, monitoring, and drift detection.
Strong FastAPI, microservices, API security, Kubernetes, Docker, Azure, CI/CD, and infrastructure-as-code experience is essential.
The ideal candidate can independently troubleshoot AI platform issues, automate operational processes, and maintain clear technical documentation.
Top 3:
1. Agentic AI, LLM Frameworks & AgentOps
Hands-on experience building production LLM agents, multi-agent workflows, RAG pipelines, and MCP integrations using LangGraph, LangChain, CrewAI, or AutoGen, including agent tracing, evaluation, and guardrails.
2. Python, FastAPI & Production MLOps
Strong Python backend development experience, including FastAPI, secure REST APIs, microservices, and production ML pipelines with model deployment, monitoring, experiment tracking, and drift detection.
3. Azure, Kubernetes, CI/CD & Platform Engineering
Experience operating containerized AI workloads using Kubernetes/AKS, Docker, GitHub Actions, Azure DevOps, and Terraform or Bicep, with strong platform troubleshooting and documentation skills.
- Salary
- 120.00
https://walkerhealthforce.com/careers/opportunities/client/40278/aiops-engineer-agentic-ai-mlops-azure-cloud-hybrid-contract/
