MLOps Engineer

About the role

We are building an enterprise‑scale, Azure‑native Document Intelligence and Retrieval‑Augmented Generation platform. The MLOps Engineer will operationalize, scale, and govern ML/LLM pipelines, ensuring reliability, security, and performance of AI workloads on Microsoft Azure and Azure OpenAI Service.

Key responsibilities

• Productionize end‑to‑end pipelines for data ingestion, classification, extraction, enrichment, and retrieval using Azure Data Factory, Azure Functions, and related services.
• Deploy, monitor, and optimize RAG pipelines with Azure OpenAI Service and LangChain, including vector search tuning with Azure AI Search.
• Implement CI/CD pipelines for prompt/configuration changes and data schema evolution using Azure Machine Learning, GitHub Actions, and Azure DevOps.
• Ensure high‑quality data ingestion from SharePoint, APIs, and batch uploads, managing schema drift and metadata consistency.
• Build monitoring and observability solutions with Azure Monitor, Log Analytics, and Application Insights to track failures, latency, token usage, and drift.
• Enforce security, compliance, and governance controls such as RBAC, private endpoints, VNet isolation, and encryption via Azure Key Vault.
• Optimize performance and cost through prompt efficiency, caching, autoscaling, and cost‑monitoring dashboards.
• Collaborate with data engineers, AI engineers, and backend teams, providing reusable MLOps templates and documentation.

Required profile

• 6+ years of experience in MLOps, ML engineering, or platform engineering.
• Strong expertise in the Microsoft Azure ecosystem.
• Proficiency in Python for building pipelines and APIs.
• Hands‑on experience with CI/CD for ML, containerization (Docker, Kubernetes), and cloud‑native orchestration.
• Experience with Azure OpenAI Service, LangChain, and Retrieval‑Augmented Generation concepts.

Required skills

• Azure Data Factory
• Azure Functions
• Azure OpenAI Service
• LangChain
• Azure AI Search
• Azure Machine Learning
• GitHub Actions / Azure DevOps
• Azure Monitor, Log Analytics, Application Insights
• Azure Blob Storage, Azure Cosmos DB
• Python
• Docker
• Kubernetes
• CI/CD pipelines
• Vector databases and embeddings
• Prompt engineering
• RAG evaluation techniques
• Graph API